Heyang Sun
70c828b87c
deepspeed zero3 QLoRA finetuning ( #11625 )
...
* deepspeed zero3 QLoRA finetuning
* Update convert.py
* Update low_bit_linear.py
* Update utils.py
* Update qlora_finetune_llama2_13b_arch_2_card.sh
* Update low_bit_linear.py
* Update alpaca_qlora_finetuning.py
* Update low_bit_linear.py
* Update utils.py
* Update convert.py
* Update alpaca_qlora_finetuning.py
* Update alpaca_qlora_finetuning.py
* Update low_bit_linear.py
* Update deepspeed_zero3.json
* Update qlora_finetune_llama2_13b_arch_2_card.sh
* Update low_bit_linear.py
* Update low_bit_linear.py
* Update utils.py
* fix style
* fix style
* Update alpaca_qlora_finetuning.py
* Update qlora_finetune_llama2_13b_arch_2_card.sh
* Update convert.py
* Update low_bit_linear.py
* Update model.py
* Update alpaca_qlora_finetuning.py
* Update low_bit_linear.py
* Update low_bit_linear.py
* Update low_bit_linear.py
2024-08-13 16:15:29 +08:00
Yishuo Wang
a184b120c9
fix minicpm-v 2.5 ( #11780 )
2024-08-13 16:14:00 +08:00
Yuwen Hu
ec184af243
Add gemma-2-2b-it and gemma-2-9b-it to igpu nightly performance test ( #11778 )
...
* add yaml and modify `concat_csv.py` for `transformers` 4.43.1 (#11758 )
* add yaml and modify `concat_csv.py` for `transformers` 4.43.1
* remove 4.43 for arc; fix;
* remove 4096-512 for 4.43
* comment some models
* Small fix
* uncomment models (#11777 )
---------
Co-authored-by: Ch1y0q <qiyue2001@gmail.com>
2024-08-13 15:39:56 +08:00
Qiyuan Gong
a88c132e54
Reduce Mistral softmax memory only in low memory mode ( #11775 )
...
* Reduce Mistral softmax memory only in low memory mode
2024-08-13 14:50:54 +08:00
Yishuo Wang
aa861df066
use new fp32 softmax kernel ( #11776 )
2024-08-13 14:48:11 +08:00
binbin Deng
23d3acdc77
Add experimental support of fused decoder layer for llama2 ( #11768 )
2024-08-13 14:41:36 +08:00
Jin, Qiao
c28b3389e6
Update npu multimodal example ( #11773 )
2024-08-13 14:14:59 +08:00
Yuwen Hu
81824ff8c9
Fix stdout in all-in-one benchmark to utf-8 ( #11772 )
2024-08-13 10:51:08 +08:00
Yishuo Wang
a1eb793f70
optimize minicpm v 2_6 firs token perf ( #11770 )
2024-08-13 09:51:18 +08:00
Yina Chen
841dbcdf3a
Fix compresskv with lookahead issue ( #11767 )
...
* fix compresskv + lookahead attn_mask qwen2
* support llama chatglm
* support mistral & chatglm
* address comments
* revert run.py
2024-08-12 18:53:55 +08:00
Yuwen Hu
f97a77ea4e
Update all-in-one benchmark for continuation task input preparation ( #11760 )
...
* All use 8192.txt for prompt preparation for now
* Small fix
* Fix text encoding mode to utf-8
* Small update
2024-08-12 17:49:45 +08:00
Xu, Shuo
1b05caba2b
Set mistral fuse rope to false except fp6 & fp16 ( #11765 )
...
* set mistral fuse rope to false except fp6 & fp16
* lint
* lint
---------
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
2024-08-12 17:25:07 +08:00
Ruonan Wang
8db34057b4
optimize lookahead init time ( #11769 )
2024-08-12 17:19:12 +08:00
Jin, Qiao
05989ad0f9
Update npu example and all in one benckmark ( #11766 )
2024-08-12 16:46:46 +08:00
Yishuo Wang
57d177738d
optimize minicpm-v-2_6 repetition penalty ( #11763 )
2024-08-12 14:10:10 +08:00
Wang, Jian4
245dba0abc
Fix lightweight-serving codegeex error ( #11759 )
2024-08-12 10:35:37 +08:00
Ruonan Wang
66fe2ee464
initial support of IPEX_LLM_PERFORMANCE_MODE ( #11754 )
...
* add perf mode
* update
* fix style
2024-08-09 19:04:09 +08:00
Yina Chen
4b9c57cc60
Support compress kv with lookahead ( #11752 )
...
* support compress kv with lookahead
* enough kv miss param
2024-08-09 17:39:57 +08:00
Yishuo Wang
93455aac09
fix minicpm V 2.6 repeat output ( #11753 )
2024-08-09 17:39:24 +08:00
Ruonan Wang
7e917d6cfb
fix gptq of llama ( #11749 )
...
* fix gptq of llama
* small fix
2024-08-09 16:39:25 +08:00
Yina Chen
dd46c141bd
Phi3 support compresskv ( #11733 )
...
* phi3 support compresskv
* fix phi3 mtl error
* fix conflict with quant kv
* fix abnormal on mtl
* fix style
* use slide windows size to compress kv
* support sliding window
* fix style
* fix style
* temp: partial support quant kv
* support quant kv with compress kv, todo: model check
* temp
* fix style
* fix style
* remove prepare
* address comment
* default -> 1.8k
2024-08-09 15:43:43 +08:00
Qiyuan Gong
d8808cc2e3
Mistral apply_rotary_pos_emb_no_cache_xpu use rope_theta from config ( #11747 )
...
mistral-7B-instruct-v0.2 and mistral-7B-instruct-v0.1 use different rope_theta (0.2 is 1e, 0.1 is 1e5). Pass self.config.rope_theta to apply_rotary_pos_emb_no_cache_xpu to avoid output difference.
2024-08-09 10:35:51 +08:00
Xiangyu Tian
044e486480
Fix vLLM CPU /chat endpoint ( #11748 )
2024-08-09 10:33:52 +08:00
Jinhe
27b4b104ed
Add qwen2-1.5b-instruct into igpu performance ( #11735 )
...
* updated qwen1.5B to all transformer==4.37 yaml
* updated qwen1.5B to all transformer==4.37 yaml
2024-08-08 16:42:18 +08:00
Shaojun Liu
107f7aafd0
enable inference mode for deepspeed tp serving ( #11742 )
2024-08-08 14:38:30 +08:00
Zijie Li
9e65cf00b3
Add openai-whisper pytorch gpu ( #11736 )
...
* Add openai-whisper pytorch gpu
* Update README.md
* Update README.md
* fix typo
* fix names update readme
* Update README.md
2024-08-08 12:32:59 +08:00
Jinhe
d0c89fb715
updated llama.cpp and ollama quickstart ( #11732 )
...
* updated llama.cpp and ollama quickstart.md
* added qwen2-1.5B sample output
* revision on quickstart updates
* revision on quickstart updates
* revision on qwen2 readme
* added 2 troubleshoots“
”
* troubleshoot revision
2024-08-08 11:04:01 +08:00
Yishuo Wang
54cc9353db
support and optimize minicpm-v-2_6 ( #11738 )
2024-08-07 18:21:16 +08:00
Yina Chen
e956e71fc1
fix conflict with quant kv ( #11737 )
2024-08-07 18:10:30 +08:00
Ruonan Wang
00a5574c8a
Use merge_qkv to replace fused_qkv for llama2 ( #11727 )
...
* update 4.38
* support new versions
* update
* fix style
* fix style
* update rope
* temp test sdpa
* fix style
* fix cpu ut
2024-08-07 18:04:01 +08:00
Yina Chen
d2abc9711b
Fix MTL 4k input qwen2 compresskv error ( #11734 )
...
* fix
* fix style
2024-08-07 16:21:57 +08:00
Yina Chen
a71ae7c22b
Support minicpm compresskv & modify default compresskv config & default enable compresskv on mtl 2.5k~4.5k ( #11726 )
...
* support minicpm & modify default & default enable on mtl 2.5k~4.5k
* fix style
2024-08-07 11:35:39 +08:00
Yishuo Wang
c093f7d980
fix phi3 ( #11729 )
2024-08-07 09:39:46 +08:00
Zijie Li
e7f7141781
Add benchmark util for transformers 4.42 ( #11725 )
...
* add new benchmark_util.py
Add new benchmark_util.py for transformers>=4.43.1. The old one renamed to benchmark_util_prev.py.
* Small fix to import code
* Update __init__.py
* fix file names
* Update lint-python
Update lint-python to exclude benchmark_util_4_29.py
benchmark_util_4_43.py
* Update benchmark_util_4_43.py
* add benchmark_util for transformers 4.42
2024-08-07 08:48:07 +08:00
Ch1y0q
4676af2054
add gemma2 example ( #11724 )
...
* add `gemma2`
* update `transformers` version
* update `README.md`
2024-08-06 21:17:50 +08:00
SichengStevenLi
985213614b
Removed no longer needed models for Arc nightly perf ( #11722 )
...
* removed LLMs that are no longer needed
Removed:
mistralai/Mistral-7B-v0.1
deepseek-ai/deepseek-coder-6.7b-instruct
* Update arc-perf-test-batch4.yaml
Removed:
deepseek-ai/deepseek-coder-6.7b-instruct
mistralai/Mistral-7B-v0.1
* Update arc-perf-test.yaml
Removed:
deepseek-ai/deepseek-coder-6.7b-instruct
mistralai/Mistral-7B-v0.1
* Create arc-perf-transformers-438.yaml
* Moved arc-perf-transformers-438.yaml location
* Create arc-perf-transformers-438-batch2.yaml
* Create arc-perf-transformers-438-batch4.yaml
* Delete python/llm/test/benchmark/arc-perf-transformers-438-batch2.yaml
* Delete python/llm/test/benchmark/arc-perf-transformers-438-batch4.yaml
* Delete python/llm/test/benchmark/arc-perf-transformers-438.yaml
2024-08-06 16:12:00 +08:00
Yishuo Wang
929675aa6b
support latest phi3 ( #11721 )
2024-08-06 15:52:55 +08:00
Jin, Qiao
11650b6f81
upgrade glm-4v example transformers version ( #11719 )
2024-08-06 14:55:09 +08:00
Yishuo Wang
bbdff6edeb
optimize internvl2 4b performance ( #11720 )
2024-08-06 14:25:08 +08:00
Yishuo Wang
f44b732aa8
support internvl2-4b ( #11718 )
2024-08-06 13:36:32 +08:00
Jin, Qiao
7f241133da
Add MiniCPM-Llama3-V-2_5 GPU example ( #11693 )
...
* Add MiniCPM-Llama3-V-2_5 GPU example
* fix
2024-08-06 10:22:41 +08:00
Jin, Qiao
808d9a7bae
Add MiniCPM-V-2 GPU example ( #11699 )
...
* Add MiniCPM-V-2 GPU example
* add example in README.md
* add example in README.md
2024-08-06 10:22:33 +08:00
Zijie Li
8fb36b9f4a
add new benchmark_util.py ( #11713 )
...
* add new benchmark_util.py
2024-08-05 16:18:48 +08:00
Wang, Jian4
493cbd9a36
Support lightweight-serving with internlm-xcomposer2-vl-7b multimodal input ( #11703 )
...
* init image_list
* enable internlm-xcomposer2 image input
* update style
* add readme
* update model
* update readme
2024-08-05 09:36:04 +08:00
Ruonan Wang
aa98ef96fe
change mixed_precision to q6_k ( #11706 )
2024-08-02 15:55:16 +08:00
Xiangyu Tian
1baa3efe0e
Optimizations for Pipeline Parallel Serving ( #11702 )
...
Optimizations for Pipeline Parallel Serving
2024-08-02 12:06:59 +08:00
Yina Chen
8d1e0bd2f4
add sdp causal support in llama ( #11705 )
2024-08-02 10:27:40 +08:00
Ruonan Wang
736a7ef72e
add sdp_causal for mistral 4.36 ( #11686 )
...
* add sdp_causal for mistral
* fix
* update
2024-08-01 18:57:31 +08:00
Yina Chen
45c730ff39
Chatglm support compresskv ( #11690 )
...
* chatglm4 support compresskv
* fix
* fix style
* support chatglm2
* fix quantkv conflict
* fix style
2024-08-01 18:20:20 +08:00
Qiyuan Gong
762ad49362
Add RANK_WAIT_TIME into DeepSpeed-AutoTP to avoid CPU memory OOM ( #11704 )
...
* DeepSpeed-AutoTP will start multiple processors to load models and convert them in CPU memory. If model/rank_num is large, this will lead to OOM. Add RANK_WAIT_TIME to reduce memory usage by controlling model reading parallelism.
2024-08-01 18:16:21 +08:00
hxsz1997
8ef4caaf5d
add 3k and 4k input of nightly perf test on iGPU ( #11701 )
...
* Add 3k&4k input in workflow for iGPU (#11685 )
* add 3k&4k input in workflow
* comment for test
* comment models for accelarate test
* remove OOM models
* modify typo
* change test model (#11696 )
* reverse test models (#11700 )
2024-08-01 14:17:46 +08:00
Guancheng Fu
afeca38a47
Fix import vllm condition ( #11682 )
2024-07-31 13:50:01 +08:00
Ruonan Wang
54bf3a23a6
add fallback for unsupported k-quants ( #11691 )
...
* add fallback
* fix style
* fix
2024-07-31 11:39:58 +08:00
Zijie Li
5079ed9e06
Add Llama3.1 example ( #11689 )
...
* Add Llama3.1 example
Add Llama3.1 example for Linux arc and Windows MTL
* Changes made to adjust compatibilities
transformers changed to 4.43.1
* Update index.rst
* Update README.md
* Update index.rst
* Update index.rst
* Update index.rst
2024-07-31 10:53:30 +08:00
Jin, Qiao
6e3ce28173
Upgrade glm-4 example transformers version ( #11659 )
...
* upgrade glm-4 example transformers version
* move pip install in one line
2024-07-31 10:24:50 +08:00
Jin, Qiao
a44ab32153
Switch to conhost when running on NPU ( #11687 )
2024-07-30 17:08:06 +08:00
Wang, Jian4
b119825152
Remove tgi parameter validation ( #11688 )
...
* remove validation
* add min warm up
* remove no need source
2024-07-30 16:37:44 +08:00
Yina Chen
670ad887fc
Qwen support compress kv ( #11680 )
...
* Qwen support compress kv
* fix style
* fix
2024-07-30 11:16:42 +08:00
hxsz1997
9b36877897
disable default quantize_kv of GQA on MTL ( #11679 )
...
* disable default quantizekv of gqa in mtl
* fix stype
* fix stype
* fix stype
* fix stype
* fix stype
* fix stype
2024-07-30 09:38:46 +08:00
Yishuo Wang
c02003925b
add mlp for gemma2 ( #11678 )
2024-07-29 16:10:23 +08:00
RyuKosei
1da1f1dd0e
Combine two versions of run_wikitext.py ( #11597 )
...
* Combine two versions of run_wikitext.py
* Update run_wikitext.py
* Update run_wikitext.py
* aligned the format
* update error display
* simplified argument parser
---------
Co-authored-by: jenniew <jenniewang123@gmail.com>
2024-07-29 15:56:16 +08:00
Yishuo Wang
6f999e6e90
add sdp for gemma2 ( #11677 )
2024-07-29 15:15:47 +08:00
Ruonan Wang
c11d5301d7
add sdp fp8 for llama ( #11671 )
...
* add sdp fp8 for llama
* fix style
* refactor
2024-07-29 13:46:22 +08:00
Yishuo Wang
7f88ce23cd
add more gemma2 optimization ( #11673 )
2024-07-29 11:13:00 +08:00
Yishuo Wang
3e8819734b
add basic gemma2 optimization ( #11672 )
2024-07-29 10:46:51 +08:00
Guoqiong Song
336dfc04b1
fix 1482 ( #11661 )
...
Co-authored-by: rnwang04 <ruonan1.wang@intel.com>
2024-07-26 12:39:09 -07:00
Heyang Sun
ba01b85c13
empty cache only for 1st token but rest token to speed up ( #11665 )
2024-07-26 16:46:21 +08:00
Yina Chen
fc7f8feb83
Support compress kv ( #11642 )
...
* mistral snapkv
* update
* mtl update
* update
* update
* update
* add comments
* style fix
* fix style
* support llama
* llama use compress kv
* support mistral 4.40
* fix style
* support diff transformers versions
* move snapkv util to kv
* fix style
* meet comments & small fix
* revert all in one
* fix indent
---------
Co-authored-by: leonardozcm <leonardo1997zcm@gmail.com>
2024-07-26 16:02:00 +08:00
Yishuo Wang
6bcdc6cc8f
fix qwen2 cpu ( #11663 )
2024-07-26 13:41:51 +08:00
Wang, Jian4
23681fbf5c
Support codegeex4-9b for lightweight-serving ( #11648 )
...
* add options, support prompt and not return end_token
* enable openai parameter
* set do_sample None and update style
2024-07-26 09:41:03 +08:00
Guancheng Fu
a4d30a8211
Change logic for detecting if vllm is available ( #11657 )
...
* fix
* fix
2024-07-25 15:24:19 +08:00
Qiyuan Gong
0c6e0b86c0
Refine continuation get input_str ( #11652 )
...
* Remove duplicate code in continuation get input_str.
* Avoid infinite loop in all-in-one due to test_length not in the list.
2024-07-25 14:41:19 +08:00
RyuKosei
2fbd375a94
update several models for nightly perf test ( #11643 )
...
Co-authored-by: Yishuo Wang <yishuo.wang@intel.com>
2024-07-25 14:06:08 +08:00
Xiangyu Tian
4499d25c26
LLM: Fix ParallelLMHead convert in vLLM cpu ( #11654 )
2024-07-25 13:07:19 +08:00
binbin Deng
777e61d8c8
Fix qwen2 & int4 on NPU ( #11646 )
2024-07-24 13:14:39 +08:00
Yishuo Wang
1b3b46e54d
fix chatglm new model ( #11639 )
2024-07-23 13:44:56 +08:00
Xu, Shuo
7f80db95eb
Change run.py in benchmark to support phi-3-vision in arc-perf ( #11638 )
...
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
2024-07-23 09:51:36 +08:00
Xiangyu Tian
060792a648
LLM: Refine Pipeline Parallel FastAPI ( #11587 )
...
Refine Pipeline Parallel FastAPI
2024-07-22 15:52:05 +08:00
Wang, Jian4
1eed0635f2
Add lightweight serving and support tgi parameter ( #11600 )
...
* init tgi request
* update openai api
* update for pp
* update and add readme
* add to docker
* add start bash
* update
* update
* update
2024-07-19 13:15:56 +08:00
Xiangyu Tian
d27a8cd08c
Fix Pipeline Parallel dtype ( #11623 )
2024-07-19 13:07:40 +08:00
Yishuo Wang
d020ad6397
add save_low_bit support for DiskEmbedding ( #11621 )
2024-07-19 10:34:53 +08:00
Guoqiong Song
380717f50d
fix gemma for 4.41 ( #11531 )
...
* fix gemma for 4.41
2024-07-18 15:02:50 -07:00
Guoqiong Song
5a6211fd56
fix minicpm for transformers>=4.39 ( #11533 )
...
* fix minicpm for transformers>=4.39
2024-07-18 15:01:57 -07:00
Yishuo Wang
0209427cf4
Add disk_embedding parameter to support put Embedding layer on CPU ( #11617 )
2024-07-18 17:06:06 +08:00
Yuwen Hu
2478e2c14b
Add check in iGPU perf workflow for results integrity ( #11616 )
...
* Add csv check for igpu benchmark workflow (#11610 )
* add csv check for igpu benchmark workflow
* ready to test
---------
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
* Restore the temporarily removed models in iGPU-perf (#11615 )
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
---------
Co-authored-by: Xu, Shuo <100334393+ATMxsp01@users.noreply.github.com>
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
2024-07-18 14:13:16 +08:00
Xiangyu Tian
4594a3dd6c
LLM: Fix DummyLayer.weight device in Pipeline Parallel ( #11612 )
2024-07-18 13:39:34 +08:00
Ruonan Wang
4da93709b1
update doc/setup to use onednn gemm for cpp ( #11598 )
...
* update doc/setup to use onednn gemm
* small fix
* Change TOC of graphrag quickstart back
2024-07-18 13:04:38 +08:00
Yishuo Wang
f4077fa905
fix llama3-8b npu long input stuck ( #11613 )
2024-07-18 11:08:17 +08:00
Zhao Changmin
e5c0058c0e
fix baichuan ( #11606 )
2024-07-18 09:43:36 +08:00
Guoqiong Song
bfcdc35b04
phi-3 on "transformers>=4.37.0,<=4.42.3" ( #11534 )
2024-07-17 17:19:57 -07:00
Guoqiong Song
d64711900a
Fix cohere model on transformers>=4.41 ( #11575 )
...
* fix cohere model for 4-41
2024-07-17 17:18:59 -07:00
Guoqiong Song
5b6eb85b85
phi model readme ( #11595 )
...
Co-authored-by: rnwang04 <ruonan1.wang@intel.com>
2024-07-17 17:18:34 -07:00
Wang, Jian4
9c15abf825
Refactor fastapi-serving and add one card serving( #11581 )
...
* init fastapi-serving one card
* mv api code to source
* update worker
* update for style-check
* add worker
* update bash
* update
* update worker name and add readme
* rename update
* rename to fastapi
2024-07-17 11:12:43 +08:00
Yishuo Wang
5837bc0014
fix chatglm3 npu output ( #11590 )
2024-07-16 18:16:30 +08:00
Guancheng Fu
06930ab258
Enable ipex-llm optimization for lm head ( #11589 )
...
* basic
* Modify convert.py
* fix
2024-07-16 16:48:44 +08:00
Heyang Sun
365adad59f
Support LoRA ChatGLM with Alpaca Dataset ( #11580 )
...
* Support LoRA ChatGLM with Alpaca Dataset
* refine
* fix
* add 2-card alpaca
2024-07-16 15:40:02 +08:00
Yina Chen
99c22745b2
fix qwen 14b fp6 abnormal output ( #11583 )
2024-07-16 10:59:00 +08:00
Yishuo Wang
c279849d27
add disk embedding api ( #11585 )
2024-07-16 10:43:39 +08:00
Xiangyu Tian
79c742dfd5
LLM: Add XPU Memory Optimizations for Pipeline Parallel ( #11567 )
...
Add XPU Memory Optimizations for Pipeline Parallel
2024-07-16 09:44:50 +08:00
Ch1y0q
50cf563a71
Add example: MiniCPM-V ( #11570 )
2024-07-15 10:55:48 +08:00
