ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
1229 commits 1 branch 0 tags 37 MiB
Commit graph

155 commits

Author SHA1 Message Date
xingyuan li
3361b66449 [LLM] Revert llm-cli to disable selecting executables on Windows (#8630) 
* revert vnni file select
* revert setup.py
* add model-api.dll
 2023-07-31 11:15:44 +09:00
binbin Deng
3dbab9087b LLM: add llama2-7b native int4 example (#8629) 2023-07-28 10:56:16 +08:00
binbin Deng
fb32fefcbe LLM: support tensor input of native int4 generate (#8620) 2023-07-27 17:59:49 +08:00
Zhao Changmin
5b484ab48d LLM: Support load_low_bit loading models in shards format (#8612) 
* shards_model

---------

Co-authored-by: leonardozcm <leonaordo1997zcm@gmail.com>
 2023-07-26 13:30:01 +08:00
binbin Deng
fcf8c085e3 LLM: add llama2-13b native int4 example (#8613) 2023-07-26 10:12:52 +08:00
Song Jiaming
650b82fa6e [LLM] add CausalLM and Speech UT (#8597) 2023-07-25 11:22:36 +08:00
Zhao Changmin
af201052db avoid malloc all missing keys in fp32 (#8600) 2023-07-25 09:48:51 +08:00
binbin Deng
3f24202e4c [LLM] Add more transformers int4 example (Llama 2) (#8602) 2023-07-25 09:21:12 +08:00
Jason Dai
0f8201c730 llm readme update (#8595) 2023-07-24 09:47:49 +08:00
Yuwen Hu
ba42a6da63 [LLM] Set torch_dtype default value to 'auto' for transformers low bit from_pretrained API 2023-07-21 17:55:00 +08:00
Yuwen Hu
bbde423349 [LLM] Add current Linux UT inference tests to nightly tests (#8578) 
* Add current inference uts to nightly tests

* Change test model from chatglm-6b to chatglm2-6b

* Add thread num env variable for nightly test

* Fix urls

* Small fix
 2023-07-21 13:26:38 +08:00
Yang Wang
feb3af0567 Optimize transformer int4 memory footprint (#8579) 2023-07-20 20:22:13 -07:00
Yang Wang
57e880f63a [LLM] use pytorch linear for large input matrix (#8492) 
* use pytorch linear for large input matrix

* only works on server

* fix style

* optimize memory

* first check server

* revert

* address comments

* fix style
 2023-07-20 09:54:25 -07:00
Yuwen Hu
6504e31a97 Small fix (#8577) 2023-07-20 16:37:04 +08:00
Yuwen Hu
2266ca7d2b [LLM] Small updates to transformers int4 ut (#8574) 
* Small fix to transformers int4 ut

* Small fix
 2023-07-20 13:20:25 +08:00
xingyuan li
7b8d9c1b0d [LLM] Add dependency file check in setup.py (#8565) 
* add package file check
 2023-07-20 14:20:08 +09:00
Song Jiaming
411d896636 LLM first transformers UT (#8514) 
* ut

* transformers api first ut

* name

* dir issue

* use chatglm instead of chatglm2

* omp

* set omp in sh

* source

* taskset

* test

* test omp

* add test
 2023-07-20 10:16:27 +08:00
Yuwen Hu
cad78740a7 [LLM] Small fixes to the Whisper transformers INT4 example (#8573) 
* Small fixes to the whisper example

* Small fix

* Small fix
 2023-07-20 10:11:33 +08:00
binbin Deng
7a9fdf74df [LLM] Add more transformers int4 example (Dolly v2) (#8571) 
* add

* add trust_remote_mode
 2023-07-19 18:20:16 +08:00
Zhao Changmin
e680af45ea LLM: Optimize Langchain Pipeline (#8561) 
* LLM: Optimize Langchain Pipeline

* load in low bit
 2023-07-19 17:43:13 +08:00
Shengsheng Huang
616b7cb0a2 add more langchain examples (#8542) 
* update langchain descriptions

* add mathchain example

* update readme

* update readme
 2023-07-19 17:42:18 +08:00
binbin Deng
457571b44e [LLM] Add more transformers int4 example (InternLM) (#8557) 2023-07-19 15:15:38 +08:00
xingyuan li
b6510fa054 fix move/download dll step (#8564) 2023-07-19 12:17:07 +09:00
xingyuan li
c52ed37745 fix starcoder dll name (#8563) 2023-07-19 11:55:06 +09:00
Zhao Changmin
3dbe3bf18e transformer_int4 (#8553) 2023-07-19 08:33:58 +08:00
Zhao Changmin
49d636e295 [LLM] whisper model transformer int4 verification and example (#8511) 
* LLM: transformer api support

* va

* example

* revert

* pep8

* pep8
 2023-07-19 08:33:20 +08:00
Yina Chen
9a7bc17ca1 [LLM] llm supports vnni link on windows (#8543) 
* support win vnni link

* fix style

* fix style

* use isa_checker

* fix

* typo

* fix

* update
 2023-07-18 16:43:45 +08:00
Yina Chen
4582b6939d [LLM]llm gptneox chat (#8527) 
* linux

* support win

* merge upstream & support vnni lib in chat
 2023-07-18 11:17:17 +08:00
Jason Dai
1ebc43b151 Update READMEs (#8554) 2023-07-18 11:06:06 +08:00
Yuwen Hu
ee70977c07 [LLM] Transformers int4 example small typo fixes (#8550) 2023-07-17 18:15:32 +08:00
Yuwen Hu
1344f50f75 [LLM] Add more transformers int4 examples (Falcon) (#8546) 
* Initial commit

* Add Falcon examples and other small fix

* Small fix

* Small fix

* Update based on comments

* Small fix
 2023-07-17 17:36:21 +08:00
Yuwen Hu
de772e7a80 Update mpt for prompt tuning (#8547) 2023-07-17 17:33:54 +08:00
binbin Deng
f1fd746722 [LLM] Add more transformers int4 example (vicuna) (#8544) 2023-07-17 16:59:55 +08:00
Xin Qiu
fccae91461 Add load_low_bit save_load_bit to AutoModelForCausalLM (#8531) 
* transformers save_low_bit load_low_bit

* update example and add readme

* update

* update

* update

* add ut

* update
 2023-07-17 15:29:55 +08:00
binbin Deng
808a64d53a [LLM] Add more transformers int4 example (starcoder) (#8540) 2023-07-17 14:41:19 +08:00
xingyuan li
e57db777e0 [LLM] Setup.py & llm-cli update for windows vnni binary files (#8537) 
* update setup.py
* update llm-cli
 2023-07-17 12:28:38 +09:00
binbin Deng
f56b5ade4c [LLM] Add more transformers int4 example (chatglm2) (#8539) 2023-07-14 17:58:33 +08:00
binbin Deng
92d33cf35a [LLM] Add more transformers int4 example (phoenix) (#8520) 2023-07-14 17:58:04 +08:00
Yuwen Hu
e0f0def279 Remove unused example for now (#8538) 2023-07-14 17:32:50 +08:00
binbin Deng
b397e40015 [LLM] Add more transformers int4 example (RedPajama) (#8523) 2023-07-14 17:30:28 +08:00
Yuwen Hu
7bf3e10415 [LLM] Add more int4 transformers examples (MOSS) (#8532) 
* Add Moss example

* Small fix
 2023-07-14 16:41:41 +08:00
Yuwen Hu
59b7287ef5 [LLM] Add more transformers int4 example (Baichuan) (#8522) 
* Add example model Baichuan

* Small updates to client windows settings

* Small refactor

* Small fix
 2023-07-14 16:41:29 +08:00
Yuwen Hu
ca6e38607c [LLM] Add more transformers examples (ChatGLM) (#8521) 
* Add example for chatglm v1 and other small fixes

* Small fix

* Small further fix

* Small fix

* Update based on comments & updates for client windows recommended settingts

* Small fix

* Small refactor

* Small fix

* Small fix

* Small fix to dolly v1

* Small fix
 2023-07-14 16:41:13 +08:00
xingyuan li
c87853233b [LLM] Add windows vnni binary build step (#8518) 
* add windows vnni build step
* update build info
* add download command
 2023-07-14 17:24:39 +09:00
Yishuo Wang
6320bf201e LLM: fix memory access violation (#8519) 2023-07-13 17:08:08 +08:00
xingyuan li
60c2c0c3dc Bug fix for merged pr #8503 (#8516) 2023-07-13 17:26:30 +09:00
Yuwen Hu
349bcb4bae [LLM] Add more transformers int4 example (Dolly v1) (#8517) 
* Initial commit for dolly v1

* Add example for Dolly v1 and other small fix

* Small output updates

* Small fix

* fix based on comments
 2023-07-13 16:13:47 +08:00
Xin Qiu
90e3d86bce rename low bit type name (#8512) 
* change qx_0 to sym_intx

* update

* fix typo

* update

* fix type

* fix style

* add python doc

* meet code review

* fix style
 2023-07-13 15:53:31 +08:00
xingyuan li
4f152b4e3a [LLM] Merge the llm.cpp build and the pypi release (#8503) 
* checkout llm.cpp to build new binary
* use artifact to get latest built binary files
* rename quantize
* modify all release workflow
 2023-07-13 16:34:24 +09:00
Yuwen Hu
bcde8ec83e [LLM] Small fix to MPT Example (#8513) 2023-07-13 14:33:21 +08:00