Shaojun Liu
a1164e45b6
Enable Release Pypi workflow to be called in another repo ( #11483 )
2024-07-01 19:48:21 +08:00
Yuwen Hu
fb4774b076
Update pull request template for manually-ttriggered Unit tests ( #11482 )
2024-07-01 19:06:29 +08:00
Yuwen Hu
ca24794dd0
Fixes for performance test triggering ( #11481 )
2024-07-01 18:39:54 +08:00
Yuwen Hu
6bdc562f4c
Enable triggering nightly tests/performance tests from another repo ( #11480 )
...
* Enable triggering from another workflow for nightly tests and example tests
* Enable triggering from another workflow for nightly performance tests
2024-07-01 17:45:42 +08:00
Yishuo Wang
ec3a912ab6
optimize npu llama long context performance ( #11478 )
2024-07-01 16:49:23 +08:00
Heyang Sun
913e750b01
fix non-string deepseed config path bug ( #11476 )
...
* fix non-string deepseed config path bug
* Update lora_finetune_chatglm.py
2024-07-01 15:53:50 +08:00
binbin Deng
48ad482d3d
Fix import error caused by pydantic on cpu ( #11474 )
2024-07-01 15:49:49 +08:00
Yuwen Hu
dbba51f455
Enable LLM UT workflow to be called in another repo ( #11475 )
...
* Enable LLM UT workflow to be called in another repo
* Small fixes
* Small fix
2024-07-01 15:26:17 +08:00
Yishuo Wang
39bcb33a67
add sdp support for stablelm 3b ( #11473 )
2024-07-01 14:56:15 +08:00
Zhao Changmin
cf8eb7b128
Init NPU quantize method and support q8_0_rtn ( #11452 )
...
* q8_0_rtn
* fix float point
2024-07-01 13:45:07 +08:00
Yishuo Wang
319a3b36b2
fix npu llama2 ( #11471 )
2024-07-01 10:14:11 +08:00
Heyang Sun
07362ffffc
ChatGLM3-6B LoRA Fine-tuning Demo ( #11450 )
...
* ChatGLM3-6B LoRA Fine-tuning Demo
* refine
* refine
* add 2-card deepspeed
* refine format
* add mpi4py and deepspeed install
2024-07-01 09:18:39 +08:00
Wang, Jian4
e000ac90c4
Add pp_serving example to serving image ( #11433 )
...
* init pp
* update
* update
* no clone ipex-llm again
2024-06-28 16:45:25 +08:00
Xiangyu Tian
fd933c92d8
Fix: Correct num_requests in benchmark for Pipeline Parallel Serving ( #11462 )
2024-06-28 16:10:51 +08:00
Wang, Jian4
b7bc1023fb
Add vllm_online_benchmark.py ( #11458 )
...
* init
* update and add
* update
2024-06-28 14:59:06 +08:00
SichengStevenLi
86b81c09d9
Table of Contents in Quickstart Files ( #11437 )
...
* fixed a minor grammar mistake
* added table of contents
* added table of contents
* changed table of contents indexing
* added table of contents
* added table of contents, changed grammar
* added table of contents
* added table of contents
* added table of contents
* added table of contents
* added table of contents
* added table of contents, modified chapter numbering
* fixed troubleshooting section redirection path
* added table of contents
* added table of contents, modified section numbering
* added table of contents, modified section numbering
* added table of contents
* added table of contents, changed title size, modified numbering
* added table of contents, changed section title size and capitalization
* added table of contents, modified section numbering
* changed table of contents syntax
* changed table of contents syntax
* changed table of contents syntax
* changed table of contents syntax
* changed table of contents syntax
* changed table of contents syntax
* changed table of contents syntax
* changed table of contents syntax
* changed table of contents syntax
* changed table of contents syntax
* changed table of contents syntax
* changed table of contents syntax
* changed table of contents syntax
* changed table of contents syntax
* changed table of contents syntax
* changed table of contents syntax
* changed table of contents syntax
* changed table of contents syntax
* changed table of contents capitalization issue
* changed table of contents capitalization issue
* changed table of contents location
* changed table of contents
* changed table of contents
* changed section capitalization
* removed comments
* removed comments
* removed comments
2024-06-28 10:41:00 +08:00
SONG Ge
a414e3ff8a
add pipeline parallel support with load_low_bit ( #11414 )
2024-06-28 10:17:56 +08:00
Cengguang Zhang
d0b801d7bc
LLM: change write mode in all-in-one benchmark. ( #11444 )
...
* LLM: change write mode in all-in-one benchmark.
* update output style.
2024-06-27 19:36:38 +08:00
binbin Deng
987017ef47
Update pipeline parallel serving for more model support ( #11428 )
2024-06-27 18:21:01 +08:00
Yishuo Wang
029ff15d28
optimize npu llama2 first token performance ( #11451 )
2024-06-27 17:37:33 +08:00
Qiyuan Gong
4e4ecd5095
Control sys.modules ipex duplicate check with BIGDL_CHECK_DUPLICATE_IMPORT ( #11453 )
...
* Control sys.modules ipex duplicate check with BIGDL_CHECK_DUPLICATE_IMPORT。
2024-06-27 17:21:45 +08:00
Yishuo Wang
c6e5ad668d
fix internlm xcomposser meta-instruction typo ( #11448 )
2024-06-27 15:29:43 +08:00
Yishuo Wang
f89ca23748
optimize npu llama2 perf again ( #11445 )
2024-06-27 15:13:42 +08:00
Shaojun Liu
13f59ae6b4
Fix llm binary build linux-build-avxvnni failure ( #11447 )
...
* skip gpg check failure
* skip gpg check
2024-06-27 14:12:14 +08:00
Yishuo Wang
cf0f5c4322
change npu document ( #11446 )
2024-06-27 13:59:59 +08:00
binbin Deng
508c364a79
Add precision option in PP inference examples ( #11440 )
2024-06-27 09:24:27 +08:00
Jason Dai
e9e8f9b4d4
Update Readme ( #11441 )
2024-06-26 19:48:07 +08:00
Jason Dai
2939f1ac60
Update README.md ( #11439 )
2024-06-26 19:25:58 +08:00
Yishuo Wang
2a0f8087e3
optimize qwen2 gpu memory usage again ( #11435 )
2024-06-26 16:52:29 +08:00
Shaojun Liu
ab9f7f3ac5
FIX: Qwen1.5-GPTQ-Int4 inference error ( #11432 )
...
* merge_qkv if quant_method is 'gptq'
* fix python style checks
* refactor
* update GPU example
2024-06-26 15:36:22 +08:00
Guancheng Fu
99cd16ef9f
Fix error while using pipeline parallism ( #11434 )
2024-06-26 15:33:47 +08:00
Yuwen Hu
a45ceac4e4
Update main readme for missing quickstarts ( #11427 )
...
* Update main readme to add missing quckstart
* Update quickstart index page
* Small fixes
* Small fix
2024-06-26 13:51:42 +08:00
Jiao Wang
40fa23560e
Fix LLAVA example on CPU ( #11271 )
...
* update
* update
* update
* update
2024-06-25 20:04:59 -07:00
Yishuo Wang
ca0e69c3a7
optimize npu llama perf again ( #11431 )
2024-06-26 10:52:54 +08:00
Yishuo Wang
9f6e5b4fba
optimize llama npu perf ( #11426 )
2024-06-25 17:43:20 +08:00
binbin Deng
e473b8d946
Add more qwen1.5 and qwen2 support for pipeline parallel inference ( #11423 )
2024-06-25 15:49:32 +08:00
binbin Deng
aacc1fd8c0
Fix shape error when run qwen1.5-14b using deepspeed autotp ( #11420 )
2024-06-25 13:48:37 +08:00
Yishuo Wang
3b23de684a
update npu examples ( #11422 )
2024-06-25 13:32:53 +08:00
Xiangyu Tian
8ddae22cfb
LLM: Refactor Pipeline-Parallel-FastAPI example ( #11319 )
...
Initially Refactor for Pipeline-Parallel-FastAPI example
2024-06-25 13:30:36 +08:00
SONG Ge
34c15d3a10
update pp document ( #11421 )
2024-06-25 10:17:20 +08:00
Xin Qiu
9e4ee61737
rename BIGDL_OPTIMIZE_LM_HEAD to IPEX_LLM_LAST_LM_HEAD and add qwen2 ( #11418 )
2024-06-24 18:42:37 +08:00
Yuwen Hu
75f836f288
Add extra warmup for THUDM/glm-4-9b-chat in igpu-performance test ( #11417 )
2024-06-24 18:08:05 +08:00
Yuwen Hu
ecb9efde65
Workaround if demo preview image load slow in mddocs ( #11412 )
...
* Small tests for demo video workaround
* Small fix
* Add workaround for langchain-chatchat demo video
* Small fix
* Small fix
* Update for other demo videos in quickstart
* Add missing for text-generation-webui quickstart
2024-06-24 16:17:50 +08:00
Shaojun Liu
5e823ef2ce
Fix nightly arc perf ( #11404 )
...
* pip install pytest for arc perf test
* trigger test
2024-06-24 15:58:41 +08:00
Yuwen Hu
ccb3fb357a
Add mddocs index ( #11411 )
2024-06-24 15:35:18 +08:00
Heyang Sun
c985912ee3
Add Deepspeed LoRA dependencies in document ( #11410 )
2024-06-24 15:29:59 +08:00
Yishuo Wang
abe53eaa4f
optimize qwen1.5/2 memory usage when running long input with fp16 ( #11403 )
2024-06-24 13:43:04 +08:00
Guoqiong Song
7507000ef2
Fix 1383 Llama model on transformers=4.41[WIP] ( #11280 )
2024-06-21 11:24:10 -07:00
Shengsheng Huang
475b0213d2
README update (API doc and FAQ and minor fixes) ( #11397 )
...
* add faq and API doc link in README.md
* add missing quickstart link
* update links in FAQ
* update links in FAQ
* update faq
* update faq text
2024-06-21 19:46:32 +08:00
SONG Ge
0c67639539
Add more examples for pipeline parallel inference ( #11372 )
...
* add more model exampels for pipelien parallel inference
* add mixtral and vicuna models
* add yi model and past_kv supprot for chatglm family
* add docs
* doc update
* add license
* update
2024-06-21 17:55:16 +08:00
