ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
1251 commits 1 branch 0 tags 37 MiB
Commit graph

1251 commits

This branch
This branch
All branches
Author SHA1 Message Date
Yishuo Wang
5837cc424a [LLM] add chatglm pybinding binary file release (#8677) 2023-08-04 11:45:27 +08:00
xingyuan li
bc4cdb07c9 Remove conda for llm workflow (#8671) 2023-08-04 12:09:42 +09:00
Yang Wang
b6468bac43 optimize chatglm2 long sequence (#8662) 
* add chatglm2

* optimize a little

* optimize chatglm long sequence

* fix style

* address comments and fix style

* fix bug
 2023-08-03 17:56:24 -07:00
Yang Wang
3407f87075 Fix llama kv cache bug (#8674) 2023-08-03 17:54:55 -07:00
Yina Chen
59903ea668 llm linux support avx & avx2 (#8669) 2023-08-03 17:10:59 +08:00
xingyuan li
110cfb5546 [LLM] Remove old windows nightly test code (#8668) 
Remove old Windows nightly test code triggered by task scheduler
Add new Windows nightly workflow for nightly testing
 2023-08-03 17:12:23 +09:00
Yina Chen
bd177ab612 [LLM] llm binary build linux add avx & avx2 (#8665) 
* llm add linux avx & avx2 release

* fix name

* update check
 2023-08-03 14:38:31 +08:00
xingyuan li
610084e3c0 [LLM] Complete windows unittest (#8611) 
* add windows nightly test workflow
* use github runner to run pr test
* model load should use lowbit
* remove tmp dir after testing
 2023-08-03 14:48:42 +09:00
binbin Deng
a15a2516e6 add (#8659) 2023-08-03 10:12:10 +08:00
Xin Qiu
0714888705 build windows avx dll (#8657) 
* windows avx

* add to actions
 2023-08-03 02:06:24 +08:00
Yina Chen
119bf6d710 [LLM] Support linux cpp dynamic load .so (#8655) 
* support linux cpp dynamic load .so

* update cli
 2023-08-02 20:15:45 +08:00
Zhao Changmin
ca998cc6f2 LLM: Mute shape mismatch output (#8601) 
* LLM: Mute shape mismatch output
 2023-08-02 16:46:22 +08:00
Yina Chen
15b3adc7ec [LLM] llm linux binary make -> cmake (#8656) 
* llm linux make -> cmake

* update

* update
 2023-08-02 16:41:54 +08:00
Zhao Changmin
04c713ef06 LLM: Disable transformer api pretraining_tp (#8645) 
* disable pretraining_tp
 2023-08-02 11:26:01 +08:00
binbin Deng
6fc31bb4cf LLM: first update descriptions for ChatGLM transformers int4 example (#8646) 2023-08-02 11:00:56 +08:00
xingyuan li
769209b7f0 Chatglm unittest disable due to missing instruction (#8650) 2023-08-02 10:28:42 +09:00
Yang Wang
cbeae97a26 Optimize Llama Attention to to reduce KV cache memory copy (#8580) 
* Optimize llama attention to reduce KV cache memory copy

* fix bug

* fix style

* remove git

* fix style

* fix style

* fix style

* fix tests

* move llama attention to another file

* revert

* fix style

* remove jit

* fix
 2023-08-01 16:37:58 -07:00
binbin Deng
39994738d1 LLM: add chat & stream chat example for ChatGLM2 transformers int4 (#8636) 2023-08-01 14:57:45 +08:00
xingyuan li
cdfbe652ca [LLM] Add chatglm support for llm-cli (#8641) 
* add chatglm build
* add llm-cli support
* update git
* install cmake
* add ut for chatglm
* add files to setup
* fix bug cause permission error when sf lack file
 2023-08-01 14:30:17 +09:00
Zhao Changmin
d6cbfc6d2c LLM: Add requirements in whisper example (#8644) 
* LLM: Add requirements in whisper example
 2023-08-01 12:07:14 +08:00
Zhao Changmin
3e10260c6d LLM: llm-convert support chatglm family (#8643) 
* convert chatglm
 2023-08-01 11:16:18 +08:00
Yina Chen
a607972c0b [LLM]LLM windows load -api.dll (#8631) 
* temp

* update

* revert setup.py
 2023-07-31 13:47:20 +08:00
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
xingyuan li
919791e406 Add needs to make sure run in order (#8621) 2023-07-26 14:16:57 +09:00
xingyuan li
e3418d7e61 [LLM] Remove concurrency group for binary build workflow (#8619) 
* remove concurrency group for nightly test
 2023-07-26 12:15:53 +09:00
binbin Deng
fcf8c085e3 LLM: add llama2-13b native int4 example (#8613) 2023-07-26 10:12:52 +08:00
xingyuan li
a98b3fe961 Fix cancel flag causing nightly builds to fail (#8618) 2023-07-26 11:11:08 +09:00
xingyuan li
7d45233825 fix trigger enable flag (#8616) 2023-07-26 10:53:03 +09:00
Guancheng Fu
07d1aee825 [PPML] add fastchat image for tdx (#8610) 2023-07-25 15:23:41 +08:00
Song Jiaming
650b82fa6e [LLM] add CausalLM and Speech UT (#8597) 2023-07-25 11:22:36 +08:00
xingyuan li
9c897ac7db [LLM] Merge redundant code in workflow (#8596) 
* modify workflow concurrency group
* Add build check to avoid repeated compilation
* remove redundant code
 2023-07-25 12:12:00 +09:00
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
xingyuan li
2eeb653c75 fix llm build workflow misspell (#8575) 2023-07-20 12:08:54 +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