ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
3073 commits 1 branch 0 tags 37 MiB
Commit graph

1515 commits

Author SHA1 Message Date
Ruonan Wang
439c834ed3
LLM: add mixed precision for lm_head (#10795) 
* add mixed_quantization

* meet code review

* update

* fix style

* meet review
 2024-04-18 19:11:31 +08:00
Yina Chen
8796401b08
Support q4k in ipex-llm (#10796) 
* support q4k

* update
 2024-04-18 18:55:28 +08:00
Ruonan Wang
0e8aac19e3
add q6k precision in ipex-llm (#10792) 
* add q6k

* add initial 16k

* update

* fix style
 2024-04-18 16:52:09 +08:00
Qiyuan Gong
e90e31719f
axolotl lora example (#10789) 
* Add axolotl lora example
* Modify readme
* Add comments in yml
 2024-04-18 16:38:32 +08:00
Wang, Jian4
14ca42a048
LLM：Fix moe indexs error on cpu (#10791) 2024-04-18 15:56:52 +08:00
Guancheng Fu
cbe7b5753f
Add vLLM[xpu] related code (#10779) 
* Add ipex-llm side change

* add runable offline_inference

* refactor to call vllm2

* Verified async server

* add new v2 example

* add README

* fix

* change dir

* refactor readme.md

* add experimental

* fix
 2024-04-18 15:29:20 +08:00
Kai Huang
053ec30737
Transformers ppl evaluation on wikitext (#10784) 
* tranformers code

* cache
 2024-04-18 15:27:18 +08:00
Wang, Jian4
209c3501e6
LLM: Optimize qwen1.5 moe model (#10706) 
* update moe block

* fix style

* enable optmize MLP

* enabel kv_cache

* enable fuse rope

* enable fused qkv

* enable flash_attention

* error sdp quantize

* use old api

* use fuse

* use xetla

* fix python style

* update moe_blocks num

* fix output error

* add cpu sdpa

* update

* update

* update
 2024-04-18 14:54:05 +08:00
Ziteng Zhang
ff040c8f01
LISA Finetuning Example (#10743) 
* enabling xetla only supports qtype=SYM_INT4 or FP8E5

* LISA Finetuning Example on gpu

* update readme

* add licence

* Explain parameters of lisa & Move backend codes to src dir

* fix style

* fix style

* update readme

* support chatglm

* fix style

* fix style

* update readme

* fix
 2024-04-18 13:48:10 +08:00
Heyang Sun
581ebf6104
GaLore Finetuning Example (#10722) 
* GaLore Finetuning Example

* Update README.md

* Update README.md

* change data to HuggingFaceH4/helpful_instructions

* Update README.md

* Update README.md

* shrink train size and delete cache before starting training to save memory

* Update README.md

* Update galore_finetuning.py

* change model to llama2 3b

* Update README.md
 2024-04-18 13:47:41 +08:00
Yang Wang
952e517db9
use config rope_theta (#10787) 
* use config rope_theta

* fix style
 2024-04-17 20:39:11 -07:00
Guancheng Fu
31ea2f9a9f
Fix wrong output for Llama models on CPU (#10742) 2024-04-18 11:07:27 +08:00
Xin Qiu
e764f9b1b1
Disable fast fused rope on UHD (#10780) 
* use decoding fast path

* update

* update

* cleanup
 2024-04-18 10:03:53 +08:00
Yina Chen
ea5b373a97
Add lookahead GPU example (#10785) 
* Add lookahead example

* fix style & attn mask

* fix typo

* address comments
 2024-04-17 17:41:55 +08:00
Wang, Jian4
a20271ffe4
LLM: Fix yi-6b fp16 error on pvc (#10781) 
* updat for yi fp16

* update

* update
 2024-04-17 16:49:59 +08:00
ZehuaCao
0646e2c062
Fix short prompt for IPEX_CPU speculative decoding cause no_attr error (#10783) 2024-04-17 16:19:57 +08:00
Cengguang Zhang
7ec82c6042
LLM: add README.md for Long-Context examples. (#10765) 
* LLM: add readme to long-context examples.

* add precision.

* update wording.

* add GPU type.

* add Long-Context example to GPU examples.

* fix comments.

* update max input length.

* update max length.

* add output length.

* fix wording.
 2024-04-17 15:34:59 +08:00
Yina Chen
766fe45222
Fix spec error caused by lookup pr (#10777) 
* Fix spec error

* remove

* fix style
 2024-04-17 11:27:35 +08:00
Qiyuan Gong
9e5069437f
Fix gradio version in axolotl example (#10776) 
* Change to gradio>=4.19.2
 2024-04-17 10:23:43 +08:00
Qiyuan Gong
f2e923b3ca
Axolotl v0.4.0 support (#10773) 
* Add Axolotl 0.4.0, remove legacy 0.3.0 support.
* replace is_torch_bf16_gpu_available
* Add HF_HUB_OFFLINE=1
* Move transformers out of requirement
* Refine readme and qlora.yml
 2024-04-17 09:49:11 +08:00
Heyang Sun
26cae0a39c
Update FLEX in Deepspeed README (#10774) 
* Update FLEX in Deepspeed README

* Update README.md
 2024-04-17 09:28:24 +08:00
Wenjing Margaret Mao
c41730e024
edit 'ppl_result does not exist' issue, delete useless code (#10767) 
* edit ppl_result not exist issue, delete useless code

* delete nonzero_min function

---------

Co-authored-by: jenniew <jenniewang123@gmail.com>
 2024-04-16 18:11:56 +08:00
Yina Chen
899d392e2f
Support prompt lookup in ipex-llm (#10768) 
* lookup init

* add lookup

* fix style

* remove redundant code

* change param name

* fix style
 2024-04-16 16:52:38 +08:00
Qiyuan Gong
d30b22a81b
Refine axolotl 0.3.0 documents and links (#10764) 
* Refine axolotl 0.3 based on comments
* Rename requirements to requirement-xpu
* Add comments for paged_adamw_32bit
* change lora_r from 8 to 16
 2024-04-16 14:47:45 +08:00
ZehuaCao
599a88db53
Add deepsped-autoTP-Fastapi serving (#10748) 
* add deepsped-autoTP-Fastapi serving

* add readme

* add license

* update

* update

* fix
 2024-04-16 14:03:23 +08:00
binbin Deng
0a62933d36
LLM: fix qwen AutoTP (#10766) 2024-04-16 09:56:17 +08:00
Cengguang Zhang
3e2662c87e
LLM: fix get env KV_CACHE_ALLOC_BLOCK_LENGTH type. (#10771) 2024-04-16 09:32:30 +08:00
Jin Qiao
73a67804a4
GPU configuration update for examples (windows pip installer, etc.) (#10762) 
* renew chatglm3-6b gpu example readme

fix

fix

fix

* fix for comments

* fix

* fix

* fix

* fix

* fix

* apply on HF-Transformers-AutoModels

* apply on PyTorch-Models

* fix

* fix
 2024-04-15 17:42:52 +08:00
yb-peng
b5209d3ec1
Update example/GPU/PyTorch-Models/Model/llava/README.md (#10757) 
* Update example/GPU/PyTorch-Models/Model/llava/README.md

* Update README.md

fix path in windows installation
 2024-04-15 13:01:37 +08:00
binbin Deng
3d561b60ac
LLM: add enable_xetla parameter for optimize_model API (#10753) 2024-04-15 12:18:25 +08:00
Jiao Wang
a9a6b6b7af
Fix baichuan-13b issue on portable zip under transformers 4.36 (#10746) 
* fix baichuan-13b issue

* update

* update
 2024-04-12 16:27:01 -07:00
Jiao Wang
9e668a5bf0
fix_internlm-chat-7b-8k repo name in examples (#10747) 2024-04-12 10:15:48 -07:00
binbin Deng
c3fc8f4b90
LLM: add bs limitation for llama softmax upcast to fp32 (#10752) 2024-04-12 15:40:25 +08:00
hxsz1997
0d518aab8d
Merge pull request #10697 from MargarettMao/ceval 
combine english and chinese, remove nan
 2024-04-12 14:37:47 +08:00
jenniew
dd0d2df5af Change fp16.csv mistral-7b-v0.1 into Mistral-7B-v0.1 2024-04-12 14:28:46 +08:00
jenniew
7309f1ddf9 Mofidy Typos 2024-04-12 14:23:13 +08:00
jenniew
cb594e1fc5 Mofidy Typos 2024-04-12 14:22:09 +08:00
jenniew
382c18e600 Mofidy Typos 2024-04-12 14:15:48 +08:00
jenniew
1a360823ce Mofidy Typos 2024-04-12 14:13:21 +08:00
jenniew
cdbb1de972 Mark Color Modification 2024-04-12 14:00:50 +08:00
jenniew
9bbfcaf736 Mark Color Modification 2024-04-12 13:30:16 +08:00
jenniew
bb34c6e325 Mark Color Modification 2024-04-12 13:26:36 +08:00
Yishuo Wang
8086554d33
use new fp16 sdp in llama and mistral (#10734) 2024-04-12 10:49:02 +08:00
Yang Wang
019293e1b9
Fuse MOE indexes computation (#10716) 
* try moe

* use c++ cpu to compute indexes

* fix style
 2024-04-11 10:12:55 -07:00
jenniew
b151a9b672 edit csv_to_html to combine en & zh 2024-04-11 17:35:36 +08:00
binbin Deng
70ed9397f9
LLM: fix AttributeError of FP16Linear (#10740) 2024-04-11 17:03:56 +08:00
Keyan (Kyrie) Zhang
1256a2cc4e
Add chatglm3 long input example (#10739) 
* Add long context input example for chatglm3

* Small fix

* Small fix

* Small fix
 2024-04-11 16:33:43 +08:00
hxsz1997
fd473ddb1b
Merge pull request #10730 from MargarettMao/MargarettMao-parent_folder 
Edit ppl update_HTML_parent_folder
 2024-04-11 15:45:24 +08:00
Qiyuan Gong
2d64630757
Remove transformers version in axolotl example (#10736) 
* Remove transformers version in axolotl requirements.txt
 2024-04-11 14:02:31 +08:00
yb-peng
2685c41318
Modify all-in-one benchmark (#10726) 
* Update 8192 prompt in all-in-one

* Add cpu_embedding param for linux api

* Update run.py

* Update README.md
 2024-04-11 13:38:50 +08:00
Xiangyu Tian
301504aa8d
Fix transformers version warning (#10732) 2024-04-11 13:12:49 +08:00
Wenjing Margaret Mao
9bec233e4d
Delete python/llm/test/benchmark/perplexity/update_html_in_parent_folder.py 
Delete due to repetition
 2024-04-11 07:21:12 +08:00
Cengguang Zhang
4b024b7aac
LLM: optimize chatglm2 8k input. (#10723) 
* LLM: optimize chatglm2 8k input.

* rename.
 2024-04-10 16:59:06 +08:00
Yuxuan Xia
cd22cb8257
Update Env check Script (#10709) 
* Update env check bash file

* Update env-check
 2024-04-10 15:06:00 +08:00
Shaojun Liu
29bf28bd6f
Upgrade python to 3.11 in Docker Image (#10718) 
* install python 3.11 for cpu-inference docker image

* update xpu-inference dockerfile

* update cpu-serving image

* update qlora image

* update lora image

* update document
 2024-04-10 14:41:27 +08:00
Qiyuan Gong
b727767f00
Add axolotl v0.3.0 with ipex-llm on Intel GPU (#10717) 
* Add axolotl v0.3.0 support on Intel GPU.
* Add finetune example on llama-2-7B with Alpaca dataset.
 2024-04-10 14:38:29 +08:00
Wang, Jian4
c9e6d42ad1
LLM: Fix chatglm3-6b-32k error (#10719) 
* fix chatglm3-6b-32k

* update style
 2024-04-10 11:24:06 +08:00
Keyan (Kyrie) Zhang
585c174e92
Read the value of KV_CACHE_ALLOC_BLOCK_LENGTH from the environment variables (#10707) 
* Read the value of KV_CACHE_ALLOC_BLOCK_LENGTH from the environment variables.

* Fix style
 2024-04-10 10:48:46 +08:00
Jiao Wang
d1eaea509f
update chatglm readme (#10659) 2024-04-09 14:24:46 -07:00
Jiao Wang
878a97077b
Fix llava example to support transformerds 4.36 (#10614) 
* fix llava example

* update
 2024-04-09 13:47:07 -07:00
Jiao Wang
1e817926ba
Fix low memory generation example issue in transformers 4.36 (#10702) 
* update cache in low memory generate

* update
 2024-04-09 09:56:52 -07:00
Yuwen Hu
97db2492c8
Update setup.py for bigdl-core-xe-esimd-21 on Windows (#10705) 
* Support bigdl-core-xe-esimd-21 for windows in setup.py

* Update setup-llm-env accordingly
 2024-04-09 18:21:21 +08:00
Zhicun
b4147a97bb
Fix dtype mismatch error (#10609) 
* fix llama

* fix

* fix code style

* add torch type in model.py

---------

Co-authored-by: arda <arda@arda-arc19.sh.intel.com>
 2024-04-09 17:50:33 +08:00
Shaojun Liu
f37a1f2a81
Upgrade to python 3.11 (#10711) 
* create conda env with python 3.11

* recommend to use Python 3.11

* update
 2024-04-09 17:41:17 +08:00
Yishuo Wang
8f45e22072
fix llama2 (#10710) 2024-04-09 17:28:37 +08:00
Yishuo Wang
e438f941f2
disable rwkv5 fp16 (#10699) 2024-04-09 16:42:11 +08:00
Cengguang Zhang
6a32216269
LLM: add llama2 8k input example. (#10696) 
* LLM: add llama2-32K example.

* refactor name.

* fix comments.

* add IPEX_LLM_LOW_MEM notes and update sample output.
 2024-04-09 16:02:37 +08:00
Wenjing Margaret Mao
289cc99cd6
Update README.md (#10700) 
Edit "summarize the results"
 2024-04-09 16:01:12 +08:00
Wenjing Margaret Mao
d3116de0db
Update README.md (#10701) 
edit "summarize the results"
 2024-04-09 15:50:25 +08:00
Chen, Zhentao
d59e0cce5c
Migrate harness to ipexllm (#10703) 
* migrate to ipexlm

* fix workflow

* fix run_multi

* fix precision map

* rename ipexlm to ipexllm

* rename bigdl to ipex  in comments
 2024-04-09 15:48:53 +08:00
Keyan (Kyrie) Zhang
1e27e08322
Modify example from fp32 to fp16 (#10528) 
* Modify example from fp32 to fp16

* Remove Falcon from fp16 example for now

* Remove MPT from fp16 example
 2024-04-09 15:45:49 +08:00
binbin Deng
44922bb5c2
LLM: support baichuan2-13b using AutoTP (#10691) 2024-04-09 14:06:01 +08:00
Yina Chen
c7422712fc
mistral 4.36 use fp16 sdp (#10704) 2024-04-09 13:50:33 +08:00
Ovo233
dcb2038aad
Enable optimization for sentence_transformers (#10679) 
* enable optimization for sentence_transformers

* fix python style check failure
 2024-04-09 12:33:46 +08:00
Yang Wang
5a1f446d3c
support fp8 in xetla (#10555) 
* support fp8 in xetla

* change name

* adjust model file

* support convert back to cpu

* factor

* fix bug

* fix style
 2024-04-08 13:22:09 -07:00
jenniew
591bae092c combine english and chinese, remove nan 2024-04-08 19:37:51 +08:00
Cengguang Zhang
7c43ac0164
LLM: optimize llama natvie sdp for split qkv tensor (#10693) 
* LLM: optimize llama natvie sdp for split qkv tensor.

* fix block real size.

* fix comment.

* fix style.

* refactor.
 2024-04-08 17:48:11 +08:00
Xin Qiu
1274cba79b
stablelm fp8 kv cache (#10672) 
* stablelm fp8 kvcache

* update

* fix

* change to fp8 matmul

* fix style

* fix

* fix

* meet code review

* add comment
 2024-04-08 15:16:46 +08:00
Yishuo Wang
65127622aa
fix UT threshold (#10689) 2024-04-08 14:58:20 +08:00
Cengguang Zhang
c0cd238e40
LLM: support llama2 8k input with w4a16. (#10677) 
* LLM: support llama2 8k input with w4a16.

* fix comment and style.

* fix style.

* fix comments and split tensor to quantized attention forward.

* fix style.

* refactor name.

* fix style.

* fix style.

* fix style.

* refactor checker name.

* refactor native sdp split qkv tensor name.

* fix style.

* fix comment rename variables.

* fix co-exist of intermedia results.
 2024-04-08 11:43:15 +08:00
Zhicun
321bc69307
Fix llamaindex ut (#10673) 
* fix llamaindex ut

* add GPU ut
 2024-04-08 09:47:51 +08:00
yb-peng
2d88bb9b4b
add test api transformer_int4_fp16_gpu (#10627) 
* add test api transformer_int4_fp16_gpu

* update config.yaml and README.md in all-in-one

* modify run.py in all-in-one

* re-order test-api

* re-order test-api in config

* modify README.md in all-in-one

* modify README.md in all-in-one

* modify config.yaml

---------

Co-authored-by: pengyb2001 <arda@arda-arc21.sh.intel.com>
Co-authored-by: ivy-lv11 <zhicunlv@gmail.com>
 2024-04-07 15:47:17 +08:00
Wang, Jian4
47cabe8fcc
LLM: Fix no return_last_logit running bigdl_ipex chatglm3 (#10678) 
* fix no return_last_logits

* update only for chatglm
 2024-04-07 15:27:58 +08:00
Wang, Jian4
9ad4b29697
LLM: CPU benchmark using tcmalloc (#10675) 2024-04-07 14:17:01 +08:00
binbin Deng
d9a1153b4e
LLM: upgrade deepspeed in AutoTP on GPU (#10647) 2024-04-07 14:05:19 +08:00
Jin Qiao
56dfcb2ade
Migrate portable zip to ipex-llm (#10617) 
* change portable zip prompt to ipex-llm

* fix chat with ui

* add no proxy
 2024-04-07 13:58:58 +08:00
Zhicun
9d8ba64c0d
Llamaindex: add tokenizer_id and support chat (#10590) 
* add tokenizer_id

* fix

* modify

* add from_model_id and from_mode_id_low_bit

* fix typo and add comment

* fix python code style

---------

Co-authored-by: pengyb2001 <284261055@qq.com>
 2024-04-07 13:51:34 +08:00
Jin Qiao
10ee786920
Replace with IPEX-LLM in example comments (#10671) 
* Replace with IPEX-LLM in example comments

* More replacement

* revert some changes
 2024-04-07 13:29:51 +08:00
Xiangyu Tian
08018a18df
Remove not-imported MistralConfig (#10670) 2024-04-07 10:32:05 +08:00
Cengguang Zhang
1a9b8204a4
LLM: support int4 fp16 chatglm2-6b 8k input. (#10648) 2024-04-07 09:39:21 +08:00
Jiao Wang
69bdbf5806
Fix vllm print error message issue (#10664) 
* update chatglm readme

* Add condition to invalidInputError

* update

* update

* style
 2024-04-05 15:08:13 -07:00
Jason Dai
29d97e4678
Update readme (#10665) 2024-04-05 18:01:57 +08:00
Xin Qiu
4c3e493b2d
fix stablelm2 1.6b (#10656) 
* fix stablelm2 1.6b

* meet code review
 2024-04-03 22:15:32 +08:00
Jin Qiao
cc8b3be11c
Add GPU and CPU example for stablelm-zephyr-3b (#10643) 
* Add example for StableLM

* fix

* add to readme
 2024-04-03 16:28:31 +08:00
Heyang Sun
6000241b10
Add Deepspeed Example of FLEX Mistral (#10640) 2024-04-03 16:04:17 +08:00
Shaojun Liu
d18dbfb097
update spr perf test (#10644) 2024-04-03 15:53:55 +08:00
Yishuo Wang
702e686901
optimize starcoder normal kv cache (#10642) 2024-04-03 15:27:02 +08:00
Xin Qiu
3a9ab8f1ae
fix stablelm logits diff (#10636) 
* fix logits diff

* Small fixes

---------

Co-authored-by: Yuwen Hu <yuwen.hu@intel.com>
 2024-04-03 15:08:12 +08:00
Zhicun
b827f534d5
Add tokenizer_id in Langchain (#10588) 
* fix low-bit

* fix

* fix style

---------

Co-authored-by: arda <arda@arda-arc12.sh.intel.com>
 2024-04-03 14:25:35 +08:00
Zhicun
f6fef09933
fix prompt format for llama-2 in langchain (#10637) 2024-04-03 14:17:34 +08:00
Jiao Wang
330d4b4f4b
update readme (#10631) 2024-04-02 23:08:02 -07:00
Kai Huang
c875b3c858
Add seq len check for llama softmax upcast to fp32 (#10629) 2024-04-03 12:05:13 +08:00
Jiao Wang
4431134ec5
update readme (#10632) 2024-04-02 19:54:30 -07:00
Jiao Wang
23e33a0ca1
Fix qwen-vl style (#10633) 
* update

* update
 2024-04-02 18:41:38 -07:00
binbin Deng
2bbd8a1548
LLM: fix llama2 FP16 & bs>1 & autotp on PVC and ARC (#10611) 2024-04-03 09:28:04 +08:00
Jiao Wang
654dc5ba57
Fix Qwen-VL example problem (#10582) 
* update

* update

* update

* update
 2024-04-02 12:17:30 -07:00
Yuwen Hu
fd384ddfb8
Optimize StableLM (#10619) 
* Initial commit for stablelm optimizations

* Small style fix

* add dependency

* Add mlp optimizations

* Small fix

* add attention forward

* Remove quantize kv for now as head_dim=80

* Add merged qkv

* fix lisence

* Python style fix

---------

Co-authored-by: qiuxin2012 <qiuxin2012cs@gmail.com>
 2024-04-02 18:58:38 +08:00
binbin Deng
27be448920
LLM: add cpu_embedding and peak memory record for deepspeed autotp script (#10621) 2024-04-02 17:32:50 +08:00
Yishuo Wang
ba8cc6bd68
optimize starcoder2-3b (#10625) 2024-04-02 17:16:29 +08:00
Shaojun Liu
a10f5a1b8d
add python style check (#10620) 
* add python style check

* fix style checks

* update runner

* add ipex-llm-finetune-qlora-cpu-k8s to manually_build workflow

* update tag to 2.1.0-SNAPSHOT
 2024-04-02 16:17:56 +08:00
Cengguang Zhang
58b57177e3
LLM: support bigdl quantize kv cache env and add warning. (#10623) 
* LLM: support bigdl quantize kv cache env and add warnning.

* fix style.

* fix comments.
 2024-04-02 15:41:08 +08:00
Kai Huang
0a95c556a1
Fix starcoder first token perf (#10612) 
* add bias check

* update
 2024-04-02 09:21:38 +08:00
Cengguang Zhang
e567956121
LLM: add memory optimization for llama. (#10592) 
* add initial memory optimization.

* fix logic.

* fix logic,

* remove env var check in mlp split.
 2024-04-02 09:07:50 +08:00
Keyan (Kyrie) Zhang
01f491757a
Modify the link in Langchain-upstream ut (#10608) 
* Modify the link in Langchain-upstream ut

* fix langchain-upstream ut
 2024-04-01 17:03:40 +08:00
Ruonan Wang
bfc1caa5e5
LLM: support iq1s for llama2-70b-hf (#10596) 2024-04-01 13:13:13 +08:00
Ruonan Wang
d6af4877dd
LLM: remove ipex.optimize for gpt-j (#10606) 
* remove ipex.optimize

* fix

* fix
 2024-04-01 12:21:49 +08:00
Yishuo Wang
437a349dd6
fix rwkv with pip installer (#10591) 2024-03-29 17:56:45 +08:00
WeiguangHan
9a83f21b86
LLM: check user env (#10580) 
* LLM: check user env

* small fix

* small fix

* small fix
 2024-03-29 17:19:34 +08:00
Keyan (Kyrie) Zhang
848fa04dd6
Fix typo in Baichuan2 example (#10589) 2024-03-29 13:31:47 +08:00
Ruonan Wang
0136fad1d4
LLM: support iq1_s (#10564) 
* init version

* update utils

* remove unsed code
 2024-03-29 09:43:55 +08:00
Qiyuan Gong
f4537798c1
Enable kv cache quantization by default for flex when 1 < batch <= 8 (#10584) 
* Enable kv cache quantization by default for flex when 1 < batch <= 8.
* Change up bound from <8 to <=8.
 2024-03-29 09:43:42 +08:00
Cengguang Zhang
b44f7adbad
LLM: Disable esimd sdp for PVC GPU when batch size>1 (#10579) 
* llm: disable esimd sdp for pvc bz>1.

* fix logic.

* fix: avoid call get device name twice.
 2024-03-28 22:55:48 +08:00
Xin Qiu
5963239b46
Fix qwen's position_ids no enough (#10572) 
* fix position_ids

* fix position_ids
 2024-03-28 17:05:49 +08:00
ZehuaCao
52a2135d83
Replace ipex with ipex-llm (#10554) 
* fix ipex with ipex_llm

* fix ipex with ipex_llm

* update

* update

* update

* update

* update

* update

* update

* update
 2024-03-28 13:54:40 +08:00
Cheen Hau, 俊豪
1c5eb14128
Update pip install to use --extra-index-url for ipex package (#10557) 
* Change to 'pip install .. --extra-index-url' for readthedocs

* Change to 'pip install .. --extra-index-url' for examples

* Change to 'pip install .. --extra-index-url' for remaining files

* Fix URL for ipex

* Add links for ipex US and CN servers

* Update ipex cpu url

* remove readme

* Update for github actions

* Update for dockerfiles
 2024-03-28 09:56:23 +08:00
binbin Deng
92dfed77be
LLM: fix abnormal output of fp16 deepspeed autotp (#10558) 2024-03-28 09:35:48 +08:00
Jason Dai
c450c85489
Delete llm/readme.md (#10569) 2024-03-27 20:06:40 +08:00
Xiangyu Tian
51d34ca68e
Fix wrong import in speculative (#10562) 2024-03-27 18:21:07 +08:00
Cheen Hau, 俊豪
f239bc329b
Specify oneAPI minor version in documentation (#10561) 2024-03-27 17:58:57 +08:00
WeiguangHan
fbeb10c796
LLM: Set different env based on different Linux kernels (#10566) 2024-03-27 17:56:33 +08:00
hxsz1997
d86477f14d
Remove native_int4 in LangChain examples (#10510) 
* rebase the modify to ipex-llm

* modify the typo
 2024-03-27 17:48:16 +08:00
Guancheng Fu
04baac5a2e
Fix fastchat top_k (#10560) 
* fix -1 top_k

* fix

* done
 2024-03-27 16:01:58 +08:00
binbin Deng
fc8c7904f0
LLM: fix torch_dtype setting of apply fp16 optimization through optimize_model (#10556) 2024-03-27 14:18:45 +08:00
Ruonan Wang
ea4bc450c4
LLM: add esimd sdp for pvc (#10543) 
* add esimd sdp for pvc

* update

* fix

* fix batch
 2024-03-26 19:04:40 +08:00
Jin Qiao
b78289a595
Remove ipex-llm dependency in readme (#10544) 2024-03-26 18:25:14 +08:00
Xiangyu Tian
11550d3f25
LLM: Add length check for IPEX-CPU speculative decoding (#10529) 
Add length check for IPEX-CPU speculative decoding.
 2024-03-26 17:47:10 +08:00
Guancheng Fu
a3b007f3b1
[Serving] Fix fastchat breaks (#10548) 
* fix fastchat

* fix doc
 2024-03-26 17:03:52 +08:00
Yishuo Wang
69a28d6b4c
fix chatglm (#10540) 2024-03-26 16:01:00 +08:00
Shaojun Liu
c563b41491
add nightly_build workflow (#10533) 
* add nightly_build workflow

* add create-job-status-badge action

* update

* update

* update

* update setup.py

* release

* revert
 2024-03-26 12:47:38 +08:00
binbin Deng
0a3e4e788f
LLM: fix mistral hidden_size setting for deepspeed autotp (#10527) 2024-03-26 10:55:44 +08:00
Xin Qiu
1dd40b429c
enable fp4 fused mlp and qkv (#10531) 
* enable fp4 fused mlp and qkv

* update qwen

* update qwen2
 2024-03-26 08:34:00 +08:00
Wang, Jian4
16b2ef49c6
Update_document by heyang (#30) 2024-03-25 10:06:02 +08:00
Wang, Jian4
a1048ca7f6
Update setup.py and add new actions and add compatible mode (#25) 
* update setup.py

* add new action

* add compatible mode
 2024-03-22 15:44:59 +08:00
Wang, Jian4
9df70d95eb
Refactor bigdl.llm to ipex_llm (#24) 
* Rename bigdl/llm to ipex_llm

* rm python/llm/src/bigdl

* from bigdl.llm to from ipex_llm
 2024-03-22 15:41:21 +08:00
Jin Qiao
cc5806f4bc LLM: add save/load example for hf-transformers (#10432) 2024-03-22 13:57:47 +08:00
Wang, Jian4
34d0a9328c LLM: Speed-up mixtral in pipeline parallel inference (#10472) 
* speed-up mixtral

* fix style
 2024-03-22 11:06:28 +08:00
Cengguang Zhang
b9d4280892 LLM: fix baichuan7b quantize kv abnormal output. (#10504) 
* fix abnormal output.

* fix style.

* fix style.
 2024-03-22 10:00:08 +08:00
Yishuo Wang
f0f317b6cf fix a typo in yuan (#10503) 2024-03-22 09:40:04 +08:00
Guancheng Fu
3a3756b51d Add FastChat bigdl_worker (#10493) 
* done

* fix format

* add licence

* done

* fix doc

* refactor folder

* add license
 2024-03-21 18:35:05 +08:00
Xin Qiu
dba7ddaab3 add sdp fp8 for qwen llama436 baichuan mistral baichuan2 (#10485) 
* add sdp fp8

* fix style

* fix qwen

* fix baichuan 13

* revert baichuan 13b and baichuan2-13b

* fix style

* update
 2024-03-21 17:23:05 +08:00
Kai Huang
30f111cd32 lm_head empty_cache for more models (#10490) 
* modify constraint

* fix style
 2024-03-21 17:11:43 +08:00
Yuwen Hu
1579ee4421 [LLM] Add nightly igpu perf test for INT4+FP16 1024-128 (#10496) 2024-03-21 16:07:06 +08:00
binbin Deng
2958ca49c0 LLM: add patching function for llm finetuning (#10247) 2024-03-21 16:01:01 +08:00
Zhicun
5b97fdb87b update deepseek example readme (#10420) 
* update readme

* update

* update readme
 2024-03-21 15:21:48 +08:00
hxsz1997
a5f35757a4 Migrate langchain rag cpu example to gpu (#10450) 
* add langchain rag on gpu

* add rag example in readme

* add trust_remote_code in TransformersEmbeddings.from_model_id

* add trust_remote_code in TransformersEmbeddings.from_model_id in cpu
 2024-03-21 15:20:46 +08:00
binbin Deng
85ef3f1d99 LLM: add empty cache in deepspeed autotp benchmark script (#10488) 2024-03-21 10:51:23 +08:00
Xiangyu Tian
5a5fd5af5b LLM: Add speculative benchmark on CPU/XPU (#10464) 
Add speculative benchmark on CPU/XPU.
 2024-03-21 09:51:06 +08:00
Ruonan Wang
28c315a5b9 LLM: fix deepspeed error of finetuning on xpu (#10484) 2024-03-21 09:46:25 +08:00
Kai Huang
021d77fd22 Remove softmax upcast fp32 in llama (#10481) 
* update

* fix style
 2024-03-20 18:17:34 +08:00
Yishuo Wang
cfdf8ad496 Fix modules_not_to_convert argument (#10483) 2024-03-20 17:47:03 +08:00
Xiangyu Tian
cbe24cc7e6 LLM: Enable BigDL IPEX Int8 (#10480) 
Enable BigDL IPEX Int8
 2024-03-20 15:59:54 +08:00
ZehuaCao
1d062e24db Update serving doc (#10475) 
* update serving doc

* add tob

* update

* update

* update

* update vllm worker
 2024-03-20 14:44:43 +08:00
Cengguang Zhang
4581e4f17f LLM: fix whiper model missing config. (#10473) 
* fix whiper model missing config.

* fix style.

* fix style.

* style.
 2024-03-20 14:22:37 +08:00
Jin Qiao
e41d556436 LLM: change fp16 benchmark to model.half (#10477) 
* LLM: change fp16 benchmark to model.half

* fix
 2024-03-20 13:38:39 +08:00
Yishuo Wang
749bedaf1e fix rwkv v5 fp16 (#10474) 2024-03-20 13:15:08 +08:00
Yuwen Hu
72bcc27da9 [LLM] Add TransformersBgeEmbeddings class in bigdl.llm.langchain.embeddings (#10459) 
* Add TransformersBgeEmbeddings class in bigdl.llm.langchain.embeddings

* Small fixes
 2024-03-19 18:04:35 +08:00
Cengguang Zhang
463a86cd5d LLM: fix qwen-vl interpolation gpu abnormal results. (#10457) 
* fix qwen-vl interpolation gpu abnormal results.

* fix style.

* update qwen-vl gpu example.

* fix comment and update example.

* fix style.
 2024-03-19 16:59:39 +08:00
Jin Qiao
e9055c32f9 LLM: fix fp16 mem record in benchmark (#10461) 
* LLM: fix fp16 mem record in benchmark

* change style
 2024-03-19 16:17:23 +08:00
Jiao Wang
f3fefdc9ce fix pad_token_id issue (#10425) 2024-03-18 23:30:28 -07:00
Yuxuan Xia
74e7490fda Fix Baichuan2 prompt format (#10334) 
* Fix Baichuan2 prompt format

* Fix Baichuan2 README

* Change baichuan2 prompt info

* Change baichuan2 prompt info
 2024-03-19 12:48:07 +08:00
Jin Qiao
0451103a43 LLM: add int4+fp16 benchmark script for windows benchmarking (#10449) 
* LLM: add fp16 for benchmark script

* remove transformer_int4_fp16_loadlowbit_gpu_win
 2024-03-19 11:11:25 +08:00
Xin Qiu
bbd749dceb qwen2 fp8 cache (#10446) 
* qwen2 fp8 cache

* fix style check
 2024-03-19 08:32:39 +08:00
Yang Wang
9e763b049c Support running pipeline parallel inference by vertically partitioning model to different devices (#10392) 
* support pipeline parallel inference

* fix logging

* remove benchmark file

* fic

* need to warmup twice

* support qwen and qwen2

* fix lint

* remove genxir

* refine
 2024-03-18 13:04:45 -07:00
Ruonan Wang
66b4bb5c5d LLM: update setup to provide cpp for windows (#10448) 2024-03-18 18:20:55 +08:00
Xiangyu Tian
dbdeaddd6a LLM: Fix log condition for BIGDL_OPT_IPEX (#10441) 
remove log for BIGDL_OPT_IPEX
 2024-03-18 16:03:51 +08:00
Wang, Jian4
1de13ea578 LLM: remove CPU english_quotes dataset and update docker example (#10399) 
* update dataset

* update readme

* update docker cpu

* update xpu docker
 2024-03-18 10:45:14 +08:00
Xin Qiu
399843faf0 Baichuan 7b fp16 sdp and qwen2 pvc sdp (#10435) 
* add baichuan sdp

* update

* baichuan2

* fix

* fix style

* revert 13b

* revert
 2024-03-18 10:15:34 +08:00
Jiao Wang
5ab52ef5b5 update (#10424) 2024-03-15 09:24:26 -07:00
Yishuo Wang
bd64488b2a add mask support for llama/chatglm fp8 sdp (#10433) 
* add mask support for fp8 sdp

* fix chatglm2 dtype

* update
 2024-03-15 17:36:52 +08:00
Keyan (Kyrie) Zhang
444b11af22 Add LangChain upstream ut test for ipynb (#10387) 
* Add LangChain upstream ut test for ipynb

* Integrate unit test for LangChain upstream ut and ipynb into one file

* Modify file name

* Remove LangChain version update in unit test

* Move Langchain upstream ut job to arc

* Modify path in .yml file

* Modify path in llm_unit_tests.yml

* Avoid create directory repeatedly
 2024-03-15 16:31:01 +08:00
Jin Qiao
ca372f6dab LLM: add save/load example for ModelScope (#10397) 
* LLM: add sl example for modelscope

* fix according to comments

* move file
 2024-03-15 15:17:50 +08:00
Xin Qiu
24473e331a Qwen2 fp16 sdp (#10427) 
* qwen2 sdp and refine

* update

* update

* fix style

* remove use_flash_attention
 2024-03-15 13:12:03 +08:00
Kai Huang
1315150e64 Add baichuan2-13b 1k to arc nightly perf (#10406) 2024-03-15 10:29:11 +08:00
Ruonan Wang
b036205be2 LLM: add fp8 sdp for chatglm2/3 (#10411) 
* add fp8 sdp for chatglm2

* fix style
 2024-03-15 09:38:18 +08:00
Wang, Jian4
fe8976a00f LLM: Support gguf models use low_bit and fix no json(#10408) 
* support others model use low_bit

* update readme

* update to add *.json
 2024-03-15 09:34:18 +08:00
Xin Qiu
cda38f85a9 Qwen fp16 sdp (#10401) 
* qwen sdp

* fix

* update

* update

* update sdp

* update

* fix style check

* add to origin type
 2024-03-15 08:51:50 +08:00
dingbaorong
1c0f7ed3fa add xpu support (#10419) 2024-03-14 17:13:48 +08:00
Heyang Sun
7d29765092 refactor qwen2 forward to enable XPU (#10409) 
* refactor awen2 forward to enable XPU

* Update qwen2.py
 2024-03-14 11:03:05 +08:00
Yuxuan Xia
f36224aac4 Fix ceval run.sh (#10410) 2024-03-14 10:57:25 +08:00
ZehuaCao
f66329e35d Fix multiple get_enable_ipex function error (#10400) 
* fix multiple get_enable_ipex function error

* remove get_enable_ipex_low_bit function
 2024-03-14 10:14:13 +08:00
Kai Huang
76e30d8ec8 Empty cache for lm_head (#10317) 
* empty cache

* add comments
 2024-03-13 20:31:53 +08:00
Ruonan Wang
2be8bbd236 LLM: add cpp option in setup.py (#10403) 
* add llama_cpp option

* meet code review
 2024-03-13 20:12:59 +08:00
Ovo233
0dbce53464 LLM: Add decoder/layernorm unit tests (#10211) 
* add decoder/layernorm unit tests

* update tests

* delete decoder tests

* address comments

* remove none type check

* restore nonetype checks

* delete nonetype checks; add decoder tests for Llama

* add gc

* deal with tuple output
 2024-03-13 19:41:47 +08:00
Yishuo Wang
06a851afa9 support new baichuan model (#10404) 2024-03-13 17:45:50 +08:00
Yuxuan Xia
a90e9b6ec2 Fix C-Eval Workflow (#10359) 
* Fix Baichuan2 prompt format

* Fix ceval workflow errors

* Fix ceval workflow error

* Fix ceval error

* Fix ceval error

* Test ceval

* Fix ceval

* Fix ceval

* Fix ceval

* Fix ceval

* Fix ceval

* Fix ceval

* Fix ceval

* Fix ceval

* Fix ceval

* Fix ceval

* Fix ceval

* Fix ceval

* Add ceval dependency test

* Fix ceval

* Fix ceval

* Test full ceval

* Test full ceval

* Fix ceval

* Fix ceval
 2024-03-13 17:23:17 +08:00
Yishuo Wang
b268baafd6 use fp8 sdp in llama (#10396) 2024-03-13 16:45:38 +08:00
Xiangyu Tian
60043a3ae8 LLM: Support Baichuan2-13b in BigDL-vLLM (#10398) 
Support Baichuan2-13b in BigDL-vLLM.
 2024-03-13 16:21:06 +08:00
Xiangyu Tian
e10de2c42d [Fix] LLM: Fix condition check error for speculative decoding on CPU (#10402) 
Fix condition check error for speculative decoding on CPU
 2024-03-13 16:05:06 +08:00
Keyan (Kyrie) Zhang
f158b49835 [LLM] Recover arc ut test for Falcon (#10385) 2024-03-13 13:31:35 +08:00
Heyang Sun
d72c0fad0d Qwen2 SDPA forward on CPU (#10395) 
* Fix Qwen1.5 CPU forward

* Update convert.py

* Update qwen2.py
 2024-03-13 13:10:03 +08:00
Yishuo Wang
ca58a69b97 fix arc rms norm UT (#10394) 2024-03-13 13:09:15 +08:00
Wang, Jian4
0193f29411 LLM : Enable gguf float16 and Yuan2 model (#10372) 
* enable float16

* add yun files

* enable yun

* enable set low_bit on yuan2

* update

* update license

* update generate

* update readme

* update python style

* update
 2024-03-13 10:19:18 +08:00
Yina Chen
f5d65203c0 First token lm_head optimization (#10318) 
* add lm head linear

* update

* address comments and fix style

* address comment
 2024-03-13 10:11:32 +08:00
Keyan (Kyrie) Zhang
7cf01e6ec8 Add LangChain upstream ut test (#10349) 
* Add LangChain upstream ut test

* Add LangChain upstream ut test

* Specify version numbers in yml script

* Correct langchain-community version
 2024-03-13 09:52:45 +08:00
Xin Qiu
28c4a8cf5c Qwen fused qkv (#10368) 
* fused qkv + rope for qwen

* quantized kv cache

* fix

* update qwen

* fixed quantized qkv

* fix

* meet code review

* update split

* convert.py

* extend when no enough kv

* fix
 2024-03-12 17:39:00 +08:00
Yishuo Wang
741c2bf1df use new rms norm (#10384) 2024-03-12 17:29:51 +08:00
Xiangyu Tian
0ded0b4b13 LLM: Enable BigDL IPEX optimization for int4 (#10319) 
Enable BigDL IPEX optimization for int4
 2024-03-12 17:08:50 +08:00
binbin Deng
5d7e044dbc LLM: add low bit option in deepspeed autotp example (#10382) 2024-03-12 17:07:09 +08:00
binbin Deng
df3bcc0e65 LLM: remove english_quotes dataset (#10370) 2024-03-12 16:57:40 +08:00
Zhao Changmin
df2b84f7de Enable kv cache on arc batch (#10308) 2024-03-12 16:46:04 +08:00
Lilac09
5809a3f5fe Add run-hbm.sh & add user guide for spr and hbm (#10357) 
* add run-hbm.sh

* add spr and hbm guide

* only support quad mode

* only support quad mode

* update special cases

* update special cases
 2024-03-12 16:15:27 +08:00
binbin Deng
5d996a5caf LLM: add benchmark script for deepspeed autotp on gpu (#10380) 2024-03-12 15:19:57 +08:00
Keyan (Kyrie) Zhang
f9c144dc4c Fix final logits ut failure (#10377) 
* Fix final logits ut failure

* Fix final logits ut failure

* Remove Falcon from completion test for now

* Remove Falcon from unit test for now
 2024-03-12 14:34:01 +08:00
Guancheng Fu
cc4148636d [FastChat-integration] Add initial implementation for loader (#10323) 
* add initial implementation for loader

* add test method for model_loader

* data

* Refine
 2024-03-12 10:54:59 +08:00
WeiguangHan
17bdb1a60b LLM: add whisper models into nightly test (#10193) 
* LLM: add whisper models into nightly test

* small fix

* small fix

* add more whisper models

* test all cases

* test specific cases

* collect the csv

* store the resut

* to html

* small fix

* small test

* test all cases

* modify whisper_csv_to_html
 2024-03-11 20:00:47 +08:00
binbin Deng
dbcfc5c2fa LLM: fix error of 'AI-ModelScope/phi-2' hosted by ModelScope hub (#10364) 2024-03-11 16:19:17 +08:00
binbin Deng
fe27a6971c LLM: update modelscope version (#10367) 2024-03-11 16:18:27 +08:00
Chen, Zhentao
a425eaabfc fix from_pretrained when device_map=None (#10361) 
* pr trigger

* fix error when device_map=None

* fix device_map=None
 2024-03-11 16:06:12 +08:00
Yina Chen
d7b765fd3f serving xpu memory opt (#10358) 2024-03-11 15:21:22 +08:00
Ruonan Wang
be29833b2b LLM: fix qwen2 (#10356) 2024-03-11 09:29:08 +08:00
Zhicun
9026c08633 Fix llamaindex AutoTokenizer bug (#10345) 
* fix tokenizer

* fix AutoTokenizer bug

* modify code style
 2024-03-08 16:24:50 +08:00
Zhicun
2a10b53d73 rename docqa.py->rag.py (#10353) 2024-03-08 16:07:09 +08:00
Keyan (Kyrie) Zhang
f1825d7408 Add RMSNorm unit test (#10190) 2024-03-08 15:51:03 +08:00
Shengsheng Huang
370c52090c Langchain readme (#10348) 
* update langchain readme

* update readme

* create new README

* Update README_nativeint4.md
 2024-03-08 14:57:24 +08:00
Keyan (Kyrie) Zhang
7a621a4db0 Fix device_map bug by raise an error when using device_map=xpu (#10340) 
* Fix device_map bug by raise an error when using device_map=xpu

* Fix sync error

* Fix python style

* Use invalidInputError instead of invalidOperationError
 2024-03-08 13:38:52 +08:00
Yishuo Wang
1ac193ba02 add rope theta argument (#10343) 2024-03-07 17:27:19 +08:00
Yuxuan Xia
0c8d3c9830 Add C-Eval HTML report (#10294) 
* Add C-Eval HTML report

* Fix C-Eval workflow pr trigger path

* Fix C-Eval workflow typos

* Add permissions to C-Eval workflow

* Fix C-Eval workflow typo

* Add pandas dependency

* Fix C-Eval workflow typo
 2024-03-07 16:44:49 +08:00
Cengguang Zhang
496d18ab6d LLM: add quantize kv cache support for baichuan 7b and 13b. (#10330) 
* add quantize kv cache for baichuan 7b and 13b.

* fix typo.

* fix.

* fix style.

* fix style.
 2024-03-07 16:17:38 +08:00
hxsz1997
b7db21414e Update llamaindex ut (#10338) 
* add test_llamaindex of gpu

* add llamaindex gpu tests bash

* add llamaindex cpu tests bash

* update name of Run LLM langchain GPU test

* import llama_index in llamaindex gpu ut

* update the dependency of test_llamaindex

* add Run LLM llamaindex GPU test

* modify import dependency of llamaindex cpu test

* add Run LLM llamaindex test

* update llama_model_path

* delete unused model path

* add LLAMA2_7B_ORIGIN_PATH in llamaindex cpu test
 2024-03-07 10:06:16 +08:00
ZehuaCao
267de7abc3 fix fschat DEP version error (#10325) 2024-03-06 16:15:27 +08:00
Yina Chen
9ea499ca68 Optimize speculative decoding PVC memory usage (#10329) 
* optimize memory

* update

* update

* update

* support other models

* update

* fix style
 2024-03-06 09:54:21 +08:00
dingbaorong
cc796848ea fix typos (#10274) 
Co-authored-by: Ariadne <wyn2000330@126.com>
 2024-03-05 18:38:22 +08:00
hxsz1997
af11c53473 Add the installation step of postgresql and pgvector on windows in LlamaIndex GPU support (#10328) 
* add the installation of postgresql and pgvector of windows

* fix some format
 2024-03-05 18:31:19 +08:00
Yishuo Wang
0011ff9f64 optimize bge large performance (#10324) 2024-03-05 17:06:03 +08:00
Shaojun Liu
178eea5009 upload bigdl-llm wheel to sourceforge for backup (#10321) 
* test: upload to sourceforge

* update scripts

* revert
 2024-03-05 16:36:01 +08:00
Cengguang Zhang
30d009bca7 LLM: support quantized kv cache for Mistral in transformers >=4.36.0 (#10326) 
* support quantize kv for mistral in transformers 4.36

* update mistral support.

* fix style.
 2024-03-05 16:23:50 +08:00
dingbaorong
1e6f0c6f1a Add llamaindex gpu example (#10314) 
* add llamaindex example

* fix core dump

* refine readme

* add trouble shooting

* refine readme

---------

Co-authored-by: Ariadne <wyn2000330@126.com>
 2024-03-05 13:36:00 +08:00
dingbaorong
fc7f10cd12 add langchain gpu example (#10277) 
* first draft

* fix

* add readme for transformer_int4_gpu

* fix doc

* check device_map

* add arc ut test

* fix ut test

* fix langchain ut

* Refine README

* fix gpu mem too high

* fix ut test

---------

Co-authored-by: Ariadne <wyn2000330@126.com>
 2024-03-05 13:33:57 +08:00
Yuwen Hu
5dbbe1a826 [LLM] Support for new arc ut runner (#10311) 
* Support for new arc ut runner

* Comment unnecessary OMP_NUM_THREADS related settings for arc uts
 2024-03-04 18:42:02 +08:00
Yuwen Hu
d45e577d8c [LLM] Test load_low_bit in iGPU perf test on Windows (#10313) 2024-03-04 18:03:57 +08:00
WeiguangHan
fd81d66047 LLM: Compress some models to save space (#10315) 
* LLM: compress some models to save space

* add deleted comments
 2024-03-04 17:53:03 +08:00
Shaojun Liu
bab2ee5f9e update nightly spr perf test (#10178) 
* update nightly spr perf test

* update

* update runner lable

* update

* update

* update folder

* revert
 2024-03-04 13:46:33 +08:00
Cengguang Zhang
ab9fc2485f LLM: add quantize kv support for llama transformer 4.36 (#10298) 
* add quantize kv support for llama transformer 4.36

* fix style.

* fix style.
 2024-03-04 10:33:35 +08:00
Xin Qiu
58208a5883 Update FAQ document. (#10300) 
* Update install_gpu.md

* Update resolve_error.md

* Update README.md

* Update resolve_error.md

* Update README.md

* Update resolve_error.md
 2024-03-04 08:35:11 +08:00
Yuwen Hu
27d9a14989 [LLM] all-on-one update: memory optimize and streaming output (#10302) 
* Memory saving for continous in-out pair run and add support for streaming output on MTL iGPU

* Small fix

* Small fix

* Add things back
 2024-03-01 18:02:30 +08:00
SONG Ge
0ab40917fb [LLM] Split merged_qk to separated q/k linear (#10299) 
* modify merge_qk_linear to separated q/k linear

* update
 2024-03-01 16:48:55 +08:00
Yang Wang
f4d7dbcde2 use fused qkv forward in qwen2 (#10185) 
* use fused qkv forward in qwen2

* support both

* fix style

* fix rope

* remove pring

* fix style

* clean up
 2024-03-01 16:46:35 +08:00
Xin Qiu
509e206de0 update doc about gemma random and unreadable output. (#10297) 
* Update install_gpu.md

* Update README.md

* Update README.md
 2024-03-01 15:41:16 +08:00
Wang, Jian4
beb9433cec LLM: Reduce speculative _ipex_optimize_model memory use (#10281) 
* use tpp

* update ipex
 2024-03-01 13:48:23 +08:00
Yuwen Hu
f0ff0eebe1 [LLM] Support quantize kv cache for Baichuan2 7B (#10280) 
* Add quatized kv cache framework for Baichuan2 7B

* Support quantize kv cache for baichuan2

* Small fix

* Fix python style
 2024-03-01 13:35:42 +08:00
SONG Ge
273de341d7 hot-fix silu error import (#10292) 2024-03-01 10:11:37 +08:00
Shengsheng Huang
bcfad555df revise llamaindex readme (#10283) 2024-02-29 17:19:23 +08:00
Xin Qiu
232273a1b5 Enable Gemma fused mlp + Gelu (#10276) 
* update llama mlp forward

* add all

* fix style check

* split

* update

* update

* update

* fix style
 2024-02-29 16:53:24 +08:00
Guancheng Fu
2d930bdca8 Add vLLM bf16 support (#10278) 
* add argument load_in_low_bit

* add docs

* modify gpu doc

* done

---------

Co-authored-by: ivy-lv11 <lvzc@lamda.nju.edu.cn>
 2024-02-29 16:33:42 +08:00
SONG Ge
13b0bc9075 [LLM] Add quantize_kv optimization for yuan2 model (#10243) 
* add initial quantize_kv support for yuan2 model

* fix yuan2 quantize_kv generation

* apply fp16 conv layer optimizations

* disable mlp for quantize_kv
 2024-02-29 16:33:26 +08:00
Zhicun
4e6cc424f1 Add LlamaIndex RAG (#10263) 
* run demo

* format code

* add llamaindex

* add custom LLM with bigdl

* update

* add readme

* begin ut

* add unit test

* add license

* add license

* revised

* update

* modify docs

* remove data folder

* update

* modify prompt

* fixed

* fixed

* fixed
 2024-02-29 15:21:19 +08:00
Jin Qiao
5d7243067c LLM: add Baichuan2-13B-Chat 2048-256 to MTL perf (#10273) 2024-02-29 13:48:55 +08:00
Ruonan Wang
a9fd20b6ba LLM: Update qkv fusion for GGUF-IQ2 (#10271) 
* first commit

* update mistral

* fix transformers==4.36.0

* fix

* disable qk for mixtral now

* fix style
 2024-02-29 12:49:53 +08:00
Jiao Wang
6fb65bb9d2 fix in transformers 4.36 (#10150) 2024-02-28 18:43:01 -08:00
Shengsheng Huang
43dac97e03 Update README.md (#10260) 2024-02-29 10:41:14 +08:00
Ruonan Wang
4b08bc1417 LLM: relax batch check of flash atttention by double check attention mask (#10270) 
* relax batch check

* fix

* fix style
 2024-02-29 09:39:55 +08:00
Yina Chen
07f36fbfcc Fix gptj failed to extend (#10269) 2024-02-29 09:39:27 +08:00
Yishuo Wang
cccb02dad1 fix baichuan2 13b 2k input (#10267) 2024-02-28 17:20:20 +08:00
Heyang Sun
7244fd1ba5 Fix Arc StarCoder wrong query_shape when input is long (#10268) 
* Fix Arc StarCoder wrong query_shape when input is long

* Update gptbigcode.py
 2024-02-28 17:07:08 +08:00
Cengguang Zhang
a4de3095f3 LLM: Support quantize kv cache in mistral. (#10261) 
* init

* update quantize kv.
 2024-02-28 14:08:08 +08:00
Shengsheng Huang
db0d129226 Revert "Add rwkv example (#9432)" (#10264) 
This reverts commit 6930422b42.
 2024-02-28 11:48:31 +08:00
Yining Wang
6930422b42 Add rwkv example (#9432) 
* codeshell fix wrong urls

* restart runner

* add RWKV CPU & GPU example (rwkv-4-world-7b)

* restart runner

* update submodule

* fix runner

* runner-test

---------

Co-authored-by: Shengsheng Huang <shengsheng.huang@intel.com>
 2024-02-28 11:41:00 +08:00
Keyan (Kyrie) Zhang
59861f73e5 Add Deepseek-6.7B (#9991) 
* Add new example Deepseek

* Add new example Deepseek

* Add new example Deepseek

* Add new example Deepseek

* Add new example Deepseek

* modify deepseek

* modify deepseek

* Add verified model in README

* Turn cpu_embedding=True in Deepseek example

---------

Co-authored-by: Shengsheng Huang <shengsheng.huang@intel.com>
 2024-02-28 11:36:39 +08:00
Yuxuan Xia
2524273198 Update AutoGen README (#10255) 
* Update AutoGen README

* Fix AutoGen README typos

* Update AutoGen README

* Update AutoGen README
 2024-02-28 11:34:45 +08:00
Zheng, Yi
2347f611cf Add cpu and gpu examples of Mamba (#9797) 
* Add mamba cpu example

* Add mamba gpu example

* Use a smaller model as the example

* minor fixes

---------

Co-authored-by: Shengsheng Huang <shengsheng.huang@intel.com>
 2024-02-28 11:33:29 +08:00
Zhao Changmin
937e1f7c74 rebase (#9104) 
Co-authored-by: leonardozcm <leonardozcm@gmail.com>
 2024-02-28 11:18:21 +08:00
JunX
4833067489 fix GPU example link in README.md (#9533) 
* fix GPU example link in README.md

* fix GPU links in llm README.md
 2024-02-28 11:13:18 +08:00
Zhicun
308e637d0d Add DeepSeek-MoE-16B-Chat (#10155) 
* dsmoe-hf add

* add dsmoe pytorch

* update README

* modify comment

* remove GPU example

* update model name

* format code
 2024-02-28 10:12:09 +08:00
Guoqiong Song
f4a2e32106 Stream llm example for both GPU and CPU (#9390) 2024-02-27 15:54:47 -08:00
Yang Wang
c581c6db30 draft mmint4 (#10031) 
change to llm.cpp

support transposed format

revert

implement qkv fuse

fix style

change to vertically pack

change to enable_xetla

fix mlp_fusion_check

remove comments

address comments

add some comments

fix style
 2024-02-27 14:55:16 -08:00
hxsz1997
cba61a2909 Add html report of ppl (#10218) 
* remove include and language option, select the corresponding dataset based on the model name in Run

* change the nightly test time

* change the nightly test time of harness and ppl

* save the ppl result to json file

* generate csv file and print table result

* generate html

* modify the way to get parent folder

* update html in parent folder

* add llm-ppl-summary and llm-ppl-summary-html

* modify echo single result

* remove download fp16.csv

* change model name of PR

* move ppl nightly related files to llm/test folder

* reformat

* seperate make_table from make_table_and_csv.py

* separate make_csv from make_table_and_csv.py

* update llm-ppl-html

* remove comment

* add Download fp16.results
 2024-02-27 17:37:08 +08:00
Zhicun
6d60982746 Env script: add license (#10257) 
* env script

* update README.md

* modify README

* modify cpu info output

* add env-check.sh

* add env-check.bat

* add windows

* modify bat

* add license
 2024-02-27 15:29:20 +08:00
Yishuo Wang
b4fa4ab46f optimize yuan 2.0 again (#10252) 2024-02-27 14:51:42 +08:00
Zhicun
03b9c4930a UX: Script to print env info (#10088) 
* env script

* update README.md

* modify README

* modify cpu info output

* add env-check.sh

* add env-check.bat

* add windows

* modify bat
 2024-02-27 14:45:36 +08:00
Keyan (Kyrie) Zhang
843fe546b0 Add CPU and GPU examples for DeciLM-7B (#9867) 
* Add cpu and gpu examples for DeciLM-7B

* Add cpu and gpu examples for DeciLM-7B

* Add DeciLM-7B to README table

* modify deciLM

* modify deciLM

* modify deciLM

* Add verified model in README

* Add cpu_embedding=True
 2024-02-27 13:15:49 +08:00
Yuwen Hu
38ae4b372f Add yuan2-2b to win igpu perf test (#10250) 2024-02-27 11:08:33 +08:00
Heyang Sun
36a9e88104 Speculative Starcoder on CPU (#10138) 
* Speculative Starcoder on CPU

* enable kv-cache pre-allocation

* refine codes

* refine

* fix style

* fix style

* fix style

* refine

* refine

* Update speculative.py

* Update gptbigcode.py

* fix style

* Update speculative.py

* enable mixed-datatype layernorm on top of torch API

* adaptive dtype

* Update README.md
 2024-02-27 09:57:29 +08:00
Yishuo Wang
a47989c860 optimize yuan 2.0 performance (#10244) 2024-02-26 17:20:10 +08:00
Wang, Jian4
6c74b99a28 LLM: Update qwen readme (#10245) 2024-02-26 17:03:09 +08:00
hxsz1997
15ad2fd72e Merge pull request #10226 from zhentaocc/fix_harness 
Fix harness
 2024-02-26 16:49:27 +08:00
Wang, Jian4
f9b75f900b LLM: Enable qwen target_model ipex (#10232) 
* change order

* enable qwen ipex

* update qwen example

* update

* fix style

* update
 2024-02-26 16:41:12 +08:00
Jin Qiao
3e6d188553 LLM: add baichuan2-13b to mtl perf (#10238) 2024-02-26 15:55:56 +08:00
Yuwen Hu
e38e29511c [LLM] Yuan2 MLP and Rotary optimization (#10231) 
* Add optimization for rotary embedding

* Add mlp fused optimizatgion

* Python style fix

* Fix rotary embedding due to logits difference

* Small fix
 2024-02-26 15:10:08 +08:00
Ziteng Zhang
ea23afc8ec [LLM]update ipex part in mistral example readme (#10239) 
* update ipex part in mistral example readme
 2024-02-26 14:35:20 +08:00
SONG Ge
df2f3885ba [LLM] Enable kv_cache and forward_qkv optimizations for yuan2 (#10225) 
* add init kv_cache support for yuan2

* add forward qkv in yuan
 2024-02-26 11:29:48 +08:00
Xiangyu Tian
85a99e13e8 LLM: Fix ChatGLM3 Speculative Example (#10236) 
Fix ChatGLM3 Speculative Example.
 2024-02-26 10:57:28 +08:00
Chen, Zhentao
213ef06691 fix readme 2024-02-24 00:38:08 +08:00
Ruonan Wang
28513f3978 LLM: support fp16 embedding & add mlp fusion for iq2_xxs (#10219) 
* add fp16 embed

* small fixes

* fix style

* fix style

* fix comment
 2024-02-23 17:26:24 +08:00
Yuwen Hu
eeecd9fc08 Python style fix (#10230) 2024-02-23 17:21:23 +08:00
Yuwen Hu
e511bbd8f1 [LLM] Add basic optimization framework for Yuan2 (#10227) 
* Add basic optimization framework for Yuan2

* Small fix

* Python style fix

* Small fix

* Small fix
 2024-02-23 17:05:00 +08:00
Xin Qiu
8ef5482da2 update Gemma readme (#10229) 
* Update README.md

* Update README.md

* Update README.md

* Update README.md
 2024-02-23 16:57:08 +08:00
Chen, Zhentao
6fe5344fa6 separate make_csv from the file 2024-02-23 16:33:38 +08:00
Chen, Zhentao
bfa98666a6 fall back to make_table.py 2024-02-23 16:33:38 +08:00
Ruonan Wang
19260492c7 LLM: fix action/installation error of mpmath (#10223) 
* fix

* test

* fix

* update
 2024-02-23 16:14:53 +08:00
Xin Qiu
aabfc06977 add gemma example (#10224) 
* add gemma gpu example

* Update README.md

* add cpu example

* Update README.md

* Update README.md

* Update generate.py

* Update generate.py
 2024-02-23 15:20:57 +08:00
yb-peng
a2c1675546 Add CPU and GPU examples for Yuan2-2B-hf (#9946) 
* Add a new CPU example of Yuan2-2B-hf

* Add a new CPU generate.py of Yuan2-2B-hf example

* Add a new GPU example of Yuan2-2B-hf

* Add Yuan2 to README table

* In CPU example:1.Use English as default prompt; 2.Provide modified files in yuan2-2B-instruct

* In GPU example:1.Use English as default prompt;2.Provide modified files

* GPU example:update README

* update Yuan2-2B-hf in README table

* Add CPU example for Yuan2-2B in Pytorch-Models

* Add GPU example for Yuan2-2B in Pytorch-Models

* Add license in generate.py; Modify README

* In GPU Add license in generate.py; Modify README

* In CPU yuan2 modify README

* In GPU yuan2 modify README

* In CPU yuan2 modify README

* In GPU example, updated the readme for Windows GPU supports

* In GPU torch example, updated the readme for Windows GPU supports

* GPU hf example README modified

* GPU example README modified
 2024-02-23 14:09:30 +08:00
yb-peng
f1f4094a09 Add CPU and GPU examples of phi-2 (#10014) 
* Add CPU and GPU examples of phi-2

* In GPU hf example, updated the readme for Windows GPU supports

* In GPU torch example, updated the readme for Windows GPU supports

* update the table in BigDL/README.md

* update the table in BigDL/python/llm/README.md
 2024-02-23 14:05:53 +08:00
Chen, Zhentao
f315c7f93a Move harness nightly related files to llm/test folder (#10209) 
* move harness nightly files to test folder

* change workflow file path accordingly

* use arc01 when pr

* fix path

* fix fp16 csv path
 2024-02-23 11:12:36 +08:00
Xin Qiu
30795bdfbc Gemma optimization: rms_norm, kv_cache, fused_rope, fused_rope+qkv (#10212) 
* gemma optimization

* update

* update

* fix style

* meet code review
 2024-02-23 10:07:24 +08:00
Guoqiong Song
63681af97e falcon for transformers 4.36 (#9960) 
* falcon for transformers 4.36
 2024-02-22 17:04:40 -08:00
Jason Dai
84d5f40936 Update README.md (#10213) 2024-02-22 17:22:59 +08:00
Yina Chen
ce5840a8b7 GPT-J rope optimization on xpu (#10182) 
* optimize

* update

* fix style & move use_fuse_rope

* add ipex version check

* fix style

* update

* fix style

* meet comments

* address comments

* fix style
 2024-02-22 16:25:12 +08:00
Xiangyu Tian
f445217d02 LLM: Update IPEX to 2.2.0+cpu and Refactor for _ipex_optimize (#10189) 
Update IPEX to 2.2.0+cpu and refactor for _ipex_optimize.
 2024-02-22 16:01:11 +08:00
Heyang Sun
c876d9b5ca Support for MPT rotary embedding (#10208) 2024-02-22 15:16:31 +08:00
Ruonan Wang
5e1fee5e05 LLM: add GGUF-IQ2 examples (#10207) 
* add iq2 examples

* small fix

* meet code review

* fix

* meet review

* small fix
 2024-02-22 14:18:45 +08:00
Yuwen Hu
21de2613ce [LLM] Add model loading time record for all-in-one benchmark (#10201) 
* Add model loading time record in csv for all-in-one benchmark

* Small fix

* Small fix to number after .
 2024-02-22 13:57:18 +08:00
Ovo233
60e11b6739 LLM: Add mlp layer unit tests (#10200) 
* add mlp layer unit tests

* add download baichuan-13b

* exclude llama for now

* install additional packages

* rename bash file

* switch to Baichuan2

* delete attention related code

* fix name errors in yml file
 2024-02-22 13:44:45 +08:00
SONG Ge
ca1166a0e5 [LLM] Add quantize kv_cache for Baichuan2-13B (#10203) 
* add quantize kv_cache for baichuan2-13b

* style fix
 2024-02-22 13:43:35 +08:00
Ruonan Wang
34ee1aa91f LLM: add esimd sdp support for chatglm3 (#10205) 
* add esimd sdp support

* fix style
 2024-02-22 13:37:16 +08:00
Yuxuan Xia
7cbc2429a6 Fix C-Eval ChatGLM loading issue (#10206) 
* Add c-eval workflow and modify running files

* Modify the chatglm evaluator file

* Modify the ceval workflow for triggering test

* Modify the ceval workflow file

* Modify the ceval workflow file

* Modify ceval workflow

* Adjust the ceval dataset download

* Add ceval workflow dependencies

* Modify ceval workflow dataset download

* Add ceval test dependencies

* Add ceval test dependencies

* Correct the result print

* Fix the nightly test trigger time

* Fix ChatGLM loading issue
 2024-02-22 10:00:43 +08:00
Yuwen Hu
94cb16fe40 [LLM] Small updates to Win GPU Install Doc (#10199) 
* Make Offline installer as default for win gpu doc for oneAPI

* Small other fixes
 2024-02-21 17:58:40 +08:00
binbin Deng
9975b029c5 LLM: add qlora finetuning example using trl.SFTTrainer (#10183) 2024-02-21 16:40:04 +08:00
Ruonan Wang
f7c96b19ef LLM: support iq2 for mixtral (#10191) 
* support name mapping for mixtral

* support mixtral mixed quantization

* fix style

* fix
 2024-02-21 16:00:29 +08:00
yb-peng
b1a97b71a9 Harness eval: Add is_last parameter and fix logical operator in highlight_vals (#10192) 
* Add is_last parameter and fix logical operator in highlight_vals

* Add script to update HTML files in parent folder

* Add running update_html_in_parent_folder.py in summarize step

* Add licence info

* Remove update_html_in_parent_folder.py in Summarize the results for pull request
 2024-02-21 14:45:32 +08:00
Zhicun
c7e839e66c Add Qwen1.5-7B-Chat (#10113) 
* add Qwen1.5-7B-Chat

* modify Qwen1.5 example

* update README

* update prompt format

* update folder name and example README

* add Chinese prompt sample output

* update link in README

* correct the link

* update transformer version
 2024-02-21 13:29:29 +08:00
Xin Qiu
56ad781f2f qwen2 cpu fix (#10187) 2024-02-21 11:23:51 +08:00
Chen, Zhentao
39d37bd042 upgrade harness package version in workflow (#10188) 
* upgrade harness

* update readme
 2024-02-21 11:21:30 +08:00
Yuwen Hu
001c13243e [LLM] Add support for low_low_bit benchmark on Windows GPU (#10167) 
* Add support for low_low_bit performance test on Windows GPU

* Small fix

* Small fix

* Save memory during converting model process

* Drop the results for first time when loading in low bit on mtl igpu for better performance

* Small fix
 2024-02-21 10:51:52 +08:00
Ziteng Zhang
276ef0e885 Speculative Ziya on CPU (#10160) 
* Speculative Ziya on CPU

* Without part of Accelerate with BIGDL_OPT_IPEX
 2024-02-21 10:30:39 +08:00
Zhao Changmin
4fbf449c2d for rwkv4 (#10179) 2024-02-21 10:11:10 +08:00
yb-peng
de3dc609ee Modify harness evaluation workflow (#10174) 
* Modify table head in harness

* Specify the file path of fp16.csv

* change run to run nightly and run pr to debug

* Modify the way to get fp16.csv to downloading from github

* Change the method to calculate diff in html table

* Change the method to calculate diff in html table

* Re-arrange job order

* Re-arrange job order

* Change limit

* Change fp16.csv  path

* Change highlight rules

* Change limit
 2024-02-20 18:55:43 +08:00
Ruonan Wang
3288acb8de LLM : Support embedding quantization (only q2k now) (#10170) 
* basic logic added

* basic support

* support save&load, update mixed strategy

* fix style

* use int8 for lm_head

* add check for xpu
 2024-02-20 16:56:57 +08:00
hxsz1997
6e10d98a8d Fix some typos (#10175) 
* add llm-ppl workflow

* update the DATASET_DIR

* test multiple precisions

* modify nightly test

* match the updated ppl code

* add matrix.include

* fix the include error

* update the include

* add more model

* update the precision of include

* update nightly time and add more models

* fix the workflow_dispatch description, change default model of pr and modify the env

* modify workflow_dispatch language options

* modify options

* modify language options

* modeify workflow_dispatch type

* modify type

* modify the type of language

* change seq_len type

* fix some typos

* revert changes to stress_test.txt
 2024-02-20 14:14:53 +08:00
Zhicun
add3899311 Add ziya CPU example (#10114) 
* ziya on CPU

* add README for ziya

* specify use_cache

* add arc CPU

* update prompt format

* update link

* add comments to emphasize use_cache

* update pip cmd
 2024-02-20 13:59:52 +08:00
binbin Deng
2bb96c775c LLM: fix device setting during saving optimized model (#10154) 2024-02-20 09:52:59 +08:00
Xin Qiu
1f6d5b9f30 enable fused rmsnorm and rope qwen2 (#10163) 
* qwen2

* change convert

* cleanup
 2024-02-20 08:33:09 +08:00
yb-peng
e31210ba00 Modify html table style and add fp16.csv in harness (#10169) 
* Specify the version of pandas in harness evaluation workflow

* Specify the version of pandas in harness evaluation workflow

* Modify html table style and add fp16.csv in harness

* Modify comments
 2024-02-19 18:13:40 +08:00
WeiguangHan
6c09aed90d LLM: add qwen_1.5_7b model for arc perf test (#10166) 
* LLM: add qwen_1.5_7b model for arc perf test

* small fix

* revert some codes
 2024-02-19 17:21:00 +08:00
Yuxuan Xia
209122559a Add Ceval workflow and modify the result printing (#10140) 
* Add c-eval workflow and modify running files

* Modify the chatglm evaluator file

* Modify the ceval workflow for triggering test

* Modify the ceval workflow file

* Modify the ceval workflow file

* Modify ceval workflow

* Adjust the ceval dataset download

* Add ceval workflow dependencies

* Modify ceval workflow dataset download

* Add ceval test dependencies

* Add ceval test dependencies

* Correct the result print
 2024-02-19 17:06:53 +08:00
Zhao Changmin
f8730e8dc1 Skip rescale rwkv linear when load_low_bit (#10164) 
* rwkv_ld
 2024-02-19 15:56:42 +08:00
Heyang Sun
3e2af5ec0a Fix IPEX Baichuan Speculative (#10162) 
* Fix IPEX Baichuan Speculative

* compatible with 13B

* Update speculative.py
 2024-02-19 15:27:34 +08:00
Yina Chen
23c91cdce6 [LLM] Add min_step_draft in speculative decoding (#10142) 
* Fix gptj kvcache & position id

* Add min_draft_tokens in speculative decoding

* fix style

* update
 2024-02-19 14:31:41 +08:00
Chen, Zhentao
14ba2c5135 Harness: remove deprecated files (#10165) 2024-02-19 14:27:49 +08:00
Wang, Jian4
d3591383d5 LLM : Add CPU chatglm3 speculative example (#10004) 
* init chatglm

* update

* update
 2024-02-19 13:38:52 +08:00
Wang, Jian4
f2417e083c LLM: enable chatglm3-6b target_model ipex (#10085) 
* init

* always make casual_mask

* not return last tensor

* update

* optimize_model = False

* enable optimized=False

* enable optimized_model=true

* speed_up ipex target_model

* remove if True

* use group_size

* update python style

* update

* update
 2024-02-19 13:38:32 +08:00
Heyang Sun
177273c1a4 IPEX Speculative Support for Baichuan2 7B (#10112) 
* IPEX Speculative Support for Baichuan2 7B

* fix license problems

* refine
 2024-02-19 09:12:57 +08:00
Yina Chen
1508d6b089 Fix gptj kvcache & position id (#10141) 2024-02-18 10:02:49 +08:00
yb-peng
b4dc33def6 In harness-evaluation workflow, add statistical tables (#10118) 
* chnage storage

* fix typo

* change label

* change label to arc03

* change needs in the last step

* add generate csv in harness/make_table_results.py

* modify needs in the last job

* add csv to html

* mfix path issue in llm-harness-summary-nightly

* modify output_path

* modify args in make_table_results.py

* modify make table command in summary

* change pr env label

* remove irrelevant code in summary; add set output path step; add limit in harness run

* re-organize code structure

* modify limit in run harness

* modify csv_to_html input path

* modify needs in summary-nightly
 2024-02-08 19:01:05 +08:00
Yishuo Wang
4d33aac7f9 quick fix qwen2 fp8 kv cache (#10135) 2024-02-08 17:04:59 +08:00
Cengguang Zhang
39d90839aa LLM: add quantize kv cache for llama. (#10086) 
* feat: add quantize kv cache for llama.

* fix style.

* add quantized attention forward function.

* revert style.

* fix style.

* fix style.

* update quantized kv cache and add quantize_qkv

* fix style.

* fix style.

* optimize quantize kv cache.

* fix style.
 2024-02-08 16:49:22 +08:00
Yishuo Wang
d848efe17c add quantize kv cache support for qwen2 (#10134) 2024-02-08 16:17:21 +08:00
SONG Ge
3f79128ed7 [LLM] Enable kv_cache optimization for Qwen2 on transformers-v4.37.0 (#10131) 
* add support for kv_cache optimization on transformers-v4.37.0

* enable attention forward

* style fix

* disable rotary for now
 2024-02-08 14:20:26 +08:00
Ruonan Wang
063dc145ac LLM: basic support for q2k (#10132) 
* basic support for q2k

* fix style
 2024-02-08 13:52:01 +08:00
binbin Deng
11fe5a87ec LLM: add Modelscope model example (#10126) 2024-02-08 11:18:07 +08:00
Cengguang Zhang
0cf6a12691 LLM: add default torch_dtype for fp16. (#10124) 
* set default torch_dtype for fp16.

* fix style.

* bug fix.

* update bug fix.
 2024-02-08 10:24:16 +08:00