ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
1303 commits 1 branch 0 tags 37 MiB
Commit graph

215 commits

Author SHA1 Message Date
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
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
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
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
Zhao Changmin
ba0da17b40 LLM: Support AutoModelForSeq2SeqLM transformer API (#8449) 
* LLM: support AutoModelForSeq2SeqLM transformer API
 2023-07-13 13:33:51 +08:00
Yishuo Wang
86b5938075 LLM: fix llm pybinding (#8509) 2023-07-13 10:27:08 +08:00
Yuwen Hu
fcc352eee3 [LLM] Add more transformers_int4 examples (MPT) (#8498) 
* Update transformers_int4 readme, and initial commit for mpt

* Update example for mpt

* Small fix and recover transformers_int4_pipeline_readme.md for now

* Update based on comments

* Small fix

* Small fix

* Update based on comments
 2023-07-13 09:41:16 +08:00
Zhao Changmin
23f6a4c21f LLM: Optimize transformer int4 loading (#8499) 
* LLM: Optimize transformer int4 loading
 2023-07-12 15:25:42 +08:00
Yishuo Wang
dd3f953288 Support vnni check (#8497) 2023-07-12 10:11:15 +08:00
Xin Qiu
cd7a980ec4 Transformer int4 add qtype, support q4_1 q5_0 q5_1 q8_0 (#8481) 
* quant in Q4 5 8

* meet code review

* update readme

* style

* update

* fix error

* fix error

* update

* fix style

* update

* Update README.md

* Add load_in_low_bit
 2023-07-12 08:23:08 +08:00
Yishuo Wang
db39d0a6b3 LLM: disable mmap by default for better performance (#8467) 2023-07-11 09:26:26 +08:00
Yuwen Hu
52c6b057d6 Initial LLM Transformers example refactor (#8491) 2023-07-10 17:53:57 +08:00
Junwei Deng
254a7aa3c4 bigdl-llm: add voice-assistant example that are migrated from langchain use-case document (#8468) 2023-07-10 16:51:45 +08:00
Yishuo Wang
98bac815e4 specify numpy version (#8489) 2023-07-10 16:50:16 +08:00
Zhao Changmin
81d655cda9 LLM: transformer int4 save and load (#8462) 
* LLM: transformer int4 save and load
 2023-07-10 16:34:41 +08:00
binbin Deng
d489775d2c LLM: fix inconsistency between output token number and max_new_token (#8479) 2023-07-07 17:31:05 +08:00
Jason Dai
bcc1eae322 Llm readme update (#8472) 2023-07-06 20:04:04 +08:00
Ruonan Wang
2f77d485d8 Llm: Initial support of langchain transformer int4 API (#8459) 
* first commit of transformer int4 and pipeline

* basic examples

temp save for embeddings

support embeddings and docqa exaple

* fix based on comment

* small fix
 2023-07-06 17:50:05 +08:00
binbin Deng
14626fe05b LLM: refactor transformers and langchain class name (#8470) 2023-07-06 17:16:44 +08:00
binbin Deng
70bc8ea8ae LLM: update langchain and cpp-python style API examples (#8456) 2023-07-06 14:36:42 +08:00
Ruonan Wang
64b38e1dc8 llm: benchmark tool for transformers int4 (separate 1st token and rest) (#8460) 
* add benchmark utils

* fix

* fix bug and add readme

* hidden latency data
 2023-07-06 09:49:52 +08:00
binbin Deng
77808fa124 LLM: fix n_batch in starcoder pybinding (#8461) 2023-07-05 17:06:50 +08:00
Yina Chen
f2bb469847 [WIP] LLm llm-cli chat mode (#8440) 
* fix timezone

* temp

* Update linux interactive mode

* modify init text for interactive mode

* meet comments

* update

* win script

* meet comments
 2023-07-05 14:04:17 +08:00
binbin Deng
1970bcf14e LLM: add readme for transformer examples (#8444) 2023-07-04 17:25:58 +08:00
binbin Deng
e54e52b438 LLM: fix n_batch in bloom pybinding (#8454) 2023-07-04 15:10:32 +08:00
Yuwen Hu
372c775cb4 [LLM] Change default runner for LLM Linux tests to the ones with AVX512 (#8448) 
* Basic change for AVX512 runner

* Remove conda channel and action rename

* Small fix

* Small fix and reduce peak convert disk space

* Define n_threads based on runner status

* Small thread num fix

* Define thread_num for cli

* test

* Add self-hosted label and other small fix
 2023-07-04 14:53:03 +08:00
Jason Dai
edf23a95be Update llm readme (#8446) 2023-07-03 16:58:44 +08:00
Jason Dai
a38f927fc0 Update README.md (#8439) 2023-07-03 14:59:55 +08:00
binbin Deng
c956a46c40 LLM: first fix example/transformers (#8438) 2023-07-03 14:13:33 +08:00
Jason Dai
e5b384aaa2 Update README.md (#8437) 2023-07-03 10:54:29 +08:00
Yang Wang
449aea7ffc Optimize transformer int4 loading memory (#8400) 
* Optimize transformer int4 loading memory

* move cast to convert

* default settting low_cpu_mem_usage
 2023-06-30 20:12:12 -07:00
Jason Dai
2da21163f8 Update llm README.md (#8431) 2023-06-30 19:41:17 +08:00
Junwei Deng
2fd751de7a LLM: add a dev tool for getting glibc/glibcxx requirement (#8399) 
* add a dev tool

* pep8 change
 2023-06-30 11:09:50 +08:00
binbin Deng
146662bc0d LLM: fix langchain windows failure (#8417) 2023-06-30 09:59:10 +08:00
Yina Chen
6251ad8934 [LLM]Windows unittest (#8356) 
* win-unittest

* update

* update

* try llama 7b

* delete llama

* update

* add red-3b

* only test red-3b

* revert

* add langchain

* add dependency

* delete langchain
 2023-06-29 14:03:12 +08:00
Yina Chen
783aea3309 [LLM] LLM windows daily test (#8328) 
* llm-win-init

* test action

* test

* add types

* update for schtasks

* update pytests

* update

* update

* update doc

* use stable ckpt from ftp instead of the converted model

* download using batch -> manually

* add starcoder test
 2023-06-28 15:02:11 +08:00
binbin Deng
ca5a4b6e3a LLM: update bloom and starcoder usage in transformers_int4_pipeline (#8406) 2023-06-28 13:15:50 +08:00
Zhao Changmin
cc76ec809a check out dir (#8395) 2023-06-27 21:28:39 +08:00
Ruonan Wang
4be784a49d LLM: add UT for starcoder (convert, inference) update examples and readme (#8379) 
* first commit to add path

* update example and readme

* update path

* fix

* update based on comment
 2023-06-27 12:12:11 +08:00
Xin Qiu
e68d631c0a gptq2ggml: support loading safetensors model. (#8401) 
* update convert gptq to ggml

* update convert gptq to ggml

* gptq to ggml

* update script

* meet code review

* meet code review
 2023-06-27 11:19:33 +08:00
Ruonan Wang
b9eae23c79 LLM: add chatglm-6b example for transformer_int4 usage (#8392) 
* add example for chatglm-6b

* fix
 2023-06-26 13:46:43 +08:00
binbin Deng
19e19efb4c LLM: raise warning instead of error when use unsupported parameters (#8382) 2023-06-26 13:23:55 +08:00
Shengsheng Huang
c113ecb929 [LLM] langchain bloom, UT's, default parameters (#8357) 
* update langchain default parameters to align w/ api

* add ut's for llm and embeddings

* update inference test script to install langchain deps

* update tests workflows

---------

Co-authored-by: leonardozcm <changmin.zhao@intel.com>
 2023-06-25 17:38:00 +08:00
Shengsheng Huang
446175cc05 transformer api refactor (#8389) 
* transformer api refactor

* fix style

* add huggingface tokenizer usage in example and make ggml tokenzizer as option 1 and huggingface tokenizer as option 2

* fix style
 2023-06-25 17:15:33 +08:00