ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
1344 commits 1 branch 0 tags 37 MiB
Commit graph

248 commits

Author SHA1 Message Date
Xin Qiu
49a39452c6 update benchmark (#8899) 2023-09-06 15:11:43 +08:00
Kai Huang
4a9ff050a1 Add qlora nf4 (#8782) 
* add nf4

* dequant nf4

* style
 2023-09-06 09:39:22 +08:00
xingyuan li
704a896e90 [LLM] Add perf test on xpu for bigdl-llm (#8866) 
* add xpu latency job
* update install way
* remove duplicated workflow
* add perf upload
 2023-09-05 17:36:24 +09:00
Zhao Changmin
95271f10e0 LLM: Rename low bit layer (#8875) 
* rename lowbit

---------

Co-authored-by: leonardozcm <leonardozcm@gmail.com>
 2023-09-05 13:21:12 +08:00
Yina Chen
74a2c2ddf5 Update optimize_model=True in llama2 chatglm2 arc examples (#8878) 
* add optimize_model=True in llama2 chatglm2 examples

* add ipex optimize in gpt-j example
 2023-09-05 10:35:37 +08:00
Jason Dai
5e58f698cd Update readthedocs (#8882) 2023-09-04 15:42:16 +08:00
Song Jiaming
7b3ac66e17 [LLM] auto performance test fix specific settings to template (#8876) 2023-09-01 15:49:04 +08:00
Yang Wang
242c9d6036 Fix chatglm2 multi-turn streamchat (#8867) 2023-08-31 22:13:49 -07:00
Song Jiaming
c06f1ca93e [LLM] auto perf test to output to csv (#8846) 2023-09-01 10:48:00 +08:00
Zhao Changmin
9c652fbe95 LLM: Whisper long segment recognize example (#8826) 
* LLM: Long segment recognize example
 2023-08-31 16:41:25 +08:00
Yishuo Wang
a232c5aa21 [LLM] add protobuf in bigdl-llm dependency (#8861) 2023-08-31 15:23:31 +08:00
xingyuan li
de6c6bb17f [LLM] Downgrade amx build gcc version and remove avx flag display (#8856) 
* downgrade to gcc 11
* remove avx display
 2023-08-31 14:08:13 +09:00
Yang Wang
3b4f4e1c3d Fix llama attention optimization for XPU (#8855) 
* Fix llama attention optimization fo XPU

* fix chatglm2

* fix typo
 2023-08-30 21:30:49 -07:00
Shengsheng Huang
7b566bf686 [LLM] add new API for optimize any pytorch models (#8827) 
* add new API for optimize any pytorch models

* change test util name

* revise API and update UT

* fix python style

* update ut config, change default value

* change defaults, disable ut transcribe
 2023-08-30 19:41:53 +08:00
Xin Qiu
8eca982301 windows add env (#8852) 2023-08-30 15:54:52 +08:00
Zhao Changmin
731916c639 LLM: Enable attempting loading method automatically (#8841) 
* enable auto load method

* warning error

* logger info

---------

Co-authored-by: leonardozcm <leonardozcm@gmail.com>
 2023-08-30 15:41:55 +08:00
Yishuo Wang
bba73ec9d2 [LLM] change chatglm native int4 checkpoint name (#8851) 2023-08-30 15:05:19 +08:00
Yina Chen
55e705a84c [LLM] Support the rest of AutoXXX classes in Transformers API (#8815) 
* add transformers auto models

* fix
 2023-08-30 11:16:14 +08:00
Zhao Changmin
887018b0f2 Update ut save&load (#8847) 
Co-authored-by: leonardozcm <leonardozcm@gmail.com>
 2023-08-30 10:32:57 +08:00
Yina Chen
3462fd5c96 Add arc gpt-j example (#8840) 2023-08-30 10:31:24 +08:00
Ruonan Wang
f42c0bad1b LLM: update GPU doc (#8845) 2023-08-30 09:24:19 +08:00
Jason Dai
aab7deab1f Reorganize GPU examples (#8844) 2023-08-30 08:32:08 +08:00
Yang Wang
a386ad984e Add Data Center GPU Flex Series to Readme (#8835) 
* Add Data Center GPU Flex Series to Readme

* remove

* update starcoder
 2023-08-29 11:19:09 -07:00
Yishuo Wang
7429ea0606 [LLM] support transformer int4 + amx int4 (#8838) 2023-08-29 17:27:18 +08:00
Ruonan Wang
ddff7a6f05 Update readme of GPU to specify oneapi version(#8820) 2023-08-29 13:14:22 +08:00
Zhao Changmin
bb31d4fe80 LLM: Implement hf low_cpu_mem_usage with 1xbinary file peak memory on transformer int4 (#8731) 
* 1x peak memory
 2023-08-29 09:33:17 +08:00
Yina Chen
35fdf94031 [LLM]Arc starcoder example (#8814) 
* arc starcoder example init

* add log

* meet comments
 2023-08-28 16:48:00 +08:00
xingyuan li
6a902b892e [LLM] Add amx build step (#8822) 
* add amx build step
 2023-08-28 17:41:18 +09:00
Ruonan Wang
eae92bc7da llm: quick fix path (#8810) 2023-08-25 16:02:31 +08:00
Ruonan Wang
0186f3ab2f llm: update all ARC int4 examples (#8809) 
* update GPU examples

* update other examples

* fix

* update based on comment
 2023-08-25 15:26:10 +08:00
Song Jiaming
b8b1b6888b [LLM] Performance test (#8796) 2023-08-25 14:31:45 +08:00
Yang Wang
9d0f6a8cce rename math.py in example to avoid conflict (#8805) 2023-08-24 21:06:31 -07:00
SONG Ge
d2926c7672 [LLM] Unify Langchain Native and Transformers LLM API (#8752) 
* deprecate BigDLNativeTransformers and add specific LMEmbedding method

* deprecate and add LM methods for langchain llms

* add native params to native langchain

* new imple for embedding

* move ut from bigdlnative to casual llm

* rename embeddings api and examples update align with usage updating

* docqa example hot-fix

* add more api docs

* add langchain ut for starcoder

* support model_kwargs for transformer methods when calling causalLM and add ut

* ut fix for transformers embedding

* update for langchain causal supporting transformers

* remove model_family in readme doc

* add model_families params to support more models

* update api docs and remove chatglm embeddings for now

* remove chatglm embeddings in examples

* new refactor for ut to add bloom and transformers llama ut

* disable llama transformers embedding ut
 2023-08-25 11:14:21 +08:00
binbin Deng
5582872744 LLM: update chatglm example to be more friendly for beginners (#8795) 2023-08-25 10:55:01 +08:00
Yina Chen
7c37424a63 Fix voice assistant example input error on Linux (#8799) 
* fix linux error

* update

* remove alsa log
 2023-08-25 10:47:27 +08:00
Yang Wang
bf3591e2ff Optimize chatglm2 for bf16 (#8725) 
* make chatglm works with bf16

* fix style

* support chatglm v1

* fix style

* fix style

* add chatglm2 file
 2023-08-24 10:04:25 -07:00
xingyuan li
c94bdd3791 [LLM] Merge windows & linux nightly test (#8756) 
* fix download statement
* add check before build wheel
* use curl to upload files
* windows unittest won't upload converted model
* split llm-cli test into windows & linux versions
* update tempdir create way
* fix nightly converted model name
* windows llm-cli starcoder test temply disabled
* remove taskset dependency
* rename llm_unit_tests_linux to llm_unit_tests
 2023-08-23 12:48:41 +09:00
Jason Dai
dcadd09154 Update llm document (#8784) 2023-08-21 22:34:44 +08:00
Yishuo Wang
611c1fb628 [LLM] change default n_threads of native int4 langchain API (#8779) 2023-08-21 13:30:12 +08:00
Yishuo Wang
3d1f2b44f8 LLM: change default n_threads of native int4 models (#8776) 2023-08-18 15:46:19 +08:00
Yishuo Wang
2ba2133613 fix starcoder chinese output (#8773) 2023-08-18 13:37:02 +08:00
binbin Deng
548f7a6cf7 LLM: update convert of llama family to support llama2-70B (#8747) 2023-08-18 09:30:35 +08:00
Yina Chen
4afea496ab support q8_0 (#8765) 2023-08-17 15:06:36 +08:00
Ruonan Wang
e9aa2bd890 LLM: reduce GPU 1st token latency and update example (#8763) 
* reduce 1st token latency

* update example

* fix

* fix style

* update readme of gpu benchmark
 2023-08-16 18:01:23 +08:00
binbin Deng
06609d9260 LLM: add qwen example on arc (#8757) 2023-08-16 17:11:08 +08:00
SONG Ge
f4164e4492 [BigDL LLM] Update readme for unifying transformers API (#8737) 
* update readme doc

* fix readthedocs error

* update comment

* update exception error info

* invalidInputError instead

* fix readme typo error and remove import error

* fix more typo
 2023-08-16 14:22:32 +08:00
Song Jiaming
c1f9af6d97 [LLM] chatglm example and transformers low-bit examples (#8751) 2023-08-16 11:41:44 +08:00
Ruonan Wang
8805186f2f LLM: add benchmark tool for gpu (#8760) 
* add benchmark tool for gpu

* update
 2023-08-16 11:22:10 +08:00
binbin Deng
97283c033c LLM: add falcon example on arc (#8742) 2023-08-15 17:38:38 +08:00
binbin Deng
8c55911308 LLM: add baichuan-13B on arc example (#8755) 2023-08-15 15:07:04 +08:00