Commit graph

41 commits

Author SHA1 Message Date
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
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
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
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
Cengguang Zhang
70ab1a6f1a
LLM: unify memory optimization env variables. (#11549)
* LLM: unify memory optimization env variables.

* fix comments.
2024-07-11 11:01:28 +08:00
Guoqiong Song
7507000ef2
Fix 1383 Llama model on transformers=4.41[WIP] (#11280) 2024-06-21 11:24:10 -07:00
Yina Chen
b6b70d1ba0
Divide core-xe packages (#11131)
* temp

* add batch

* fix style

* update package name

* fix style

* add workflow

* use temp version to run uts

* trigger performance test

* trigger win igpu perf

* revert workflow & setup
2024-05-28 12:00:18 +08:00
SONG Ge
192ae35012
Add support for llama2 quantize_kv with transformers 4.38.0 (#11054)
* add support for llama2 quantize_kv with transformers 4.38.0

* fix code style

* fix code style
2024-05-16 22:23:39 +08:00
SONG Ge
16b2a418be
hotfix native_sdp ut (#11046)
* hotfix native_sdp

* update
2024-05-16 17:15:37 +08:00
SONG Ge
9942a4ba69
[WIP] Support llama2 with transformers==4.38.0 (#11024)
* support llama2 with transformers==4.38.0

* add supprot for quantize_qkv

* add original support for 4.38.0 now

* code style fix
2024-05-15 18:07:00 +08:00
Yishuo Wang
170e3d65e0
use new sdp and fp32 sdp (#11007) 2024-05-14 14:29:18 +08:00
Cengguang Zhang
75dbf240ec
LLM: update split tensor conditions. (#10872)
* LLM: update split tensor condition.

* add cond for split tensor.

* update priority of env.

* fix style.

* update env name.
2024-04-30 17:07:21 +08:00
Yishuo Wang
d884c62dc4
remove new_layout parameter (#10906) 2024-04-29 10:31:50 +08:00
Guancheng Fu
c9fac8c26b
Fix sdp logic (#10896)
* fix

* fix
2024-04-28 22:02:14 +08:00
Cengguang Zhang
9752ffe979
LLM: update split qkv native sdp. (#10895)
* LLM: update split qkv native sdp.

* fix typo.
2024-04-26 18:47:35 +08:00
Yina Chen
dc27b3bc35
Use sdp when rest token seq_len > 1 in llama & mistral (for lookup & spec) (#10790)
* update sdp condition

* update

* fix

* update & test llama

* mistral

* fix style

* update

* fix style

* remove pvc constrain

* update ds on arc

* fix style
2024-04-24 17:24:01 +08:00
Cengguang Zhang
763413b7e1
LLM: support llama split tensor for long context in transformers>=4.36. (#10844)
* LLm: support llama split tensor for long context in transformers>=4.36.

* fix dtype.

* fix style.

* fix style.

* fix style.

* fix style.

* fix dtype.

* fix style.
2024-04-23 16:13:25 +08:00
Guancheng Fu
caf75beef8
Disable sdpa (#10814) 2024-04-19 17:33:18 +08:00
Yishuo Wang
08458b4f74
remove rms norm copy (#10793) 2024-04-19 13:57:48 +08:00
Ruonan Wang
754b0ffecf Fix pvc llama (#10798)
* ifx

* update
2024-04-18 10:44:57 -07:00
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
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
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
Cengguang Zhang
3e2662c87e
LLM: fix get env KV_CACHE_ALLOC_BLOCK_LENGTH type. (#10771) 2024-04-16 09:32:30 +08:00
binbin Deng
c3fc8f4b90
LLM: add bs limitation for llama softmax upcast to fp32 (#10752) 2024-04-12 15:40:25 +08:00
Yishuo Wang
8086554d33
use new fp16 sdp in llama and mistral (#10734) 2024-04-12 10:49:02 +08:00
Jiao Wang
878a97077b
Fix llava example to support transformerds 4.36 (#10614)
* fix llava example

* update
2024-04-09 13:47:07 -07:00
Yishuo Wang
8f45e22072
fix llama2 (#10710) 2024-04-09 17:28:37 +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
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
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
Kai Huang
c875b3c858
Add seq len check for llama softmax upcast to fp32 (#10629) 2024-04-03 12:05:13 +08:00
binbin Deng
2bbd8a1548
LLM: fix llama2 FP16 & bs>1 & autotp on PVC and ARC (#10611) 2024-04-03 09:28:04 +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
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
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
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
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
Renamed from python/llm/src/bigdl/llm/transformers/models/llama.py (Browse further)