Cheen Hau, 俊豪
b2aa267f50
Enhance LLM GPU installation document ( #9828 )
...
* Improve gpu install doc
* Add troubleshooting - setvars.sh not done properly.
* Further improvements
* 2024.x.x -> 2024.0
* Fixes
* Fix Install BigDL-LLM From Wheel : bigdl-llm[xpu_2.0]
* Remove "export USE_XETLA=OFF" for Max GPU
2024-01-09 16:30:50 +08:00
dingbaorong
f6bb4ab313
Arc stress test ( #9795 )
...
* add arc stress test
* triger ci
* triger CI
* triger ci
* disable ci
2023-12-27 21:02:41 +08:00
Shaojun Liu
6c75c689ea
bigdl-llm stress test for stable version ( #9781 )
...
* 1k-512 2k-512 baseline
* add cpu stress test
* update yaml name
* update
* update
* clean up
* test
* update
* update
* update
* test
* update
2023-12-27 15:40:53 +08:00
dingbaorong
5cfb4c4f5b
Arc stable version performance regression test ( #9785 )
...
* add arc stable version regression test
* empty gpu mem between different models
* triger ci
* comment spr test
* triger ci
* address kai's comments and disable ci
* merge fp8 and int4
* disable ci
2023-12-27 11:01:56 +08:00
WeiguangHan
c05d7e1532
LLM: add star_corder_15.5b model ( #9772 )
...
* LLM: add star_corder_15.5b model
* revert llm_performance_tests.yml
2023-12-26 18:55:56 +08:00
dingbaorong
64d05e581c
add peak gpu mem stats in transformer_int4_gpu ( #9766 )
...
* add peak gpu mem stats in transformer_int4_gpu
* address weiguang's comments
2023-12-26 15:38:28 +08:00
Chen, Zhentao
7fd7c37e1b
Enable fp8e5 harness ( #9761 )
...
* fix precision format like fp8e5
* match fp8_e5m2
2023-12-22 16:59:48 +08:00
WeiguangHan
474c099559
LLM: using separate threads to do inference ( #9727 )
...
* using separate threads to do inference
* resolve some comments
* resolve some comments
* revert llm_performance_tests.yml file
2023-12-21 17:56:43 +08:00
Chen, Zhentao
b06a3146c8
Fix 70b oom ( #9738 )
...
* add default value to bigdl llm
* fix model oom
2023-12-21 10:40:52 +08:00
WeiguangHan
3e8d198b57
LLM: add eval func ( #9662 )
...
* Add eval func
* add left eval
2023-12-14 14:59:02 +08:00
Yuwen Hu
cbdd49f229
[LLM] win igpu performance for ipex 2.1 and oneapi 2024.0 ( #9679 )
...
* Change igpu win tests for ipex 2.1 and oneapi 2024.0
* Qwen model repo id updates; updates model list for 512-64
* Add .eval for win igpu all-in-one benchmark for best performance
2023-12-13 18:52:29 +08:00
Mingyu Wei
16febc949c
[LLM] Add exclude option in all-in-one performance test ( #9632 )
...
* add exclude option in all-in-one perf test
* update arc-perf-test.yaml
* Exclude in_out_pairs in main function
* fix some bugs
* address Kai's comments
* define excludes at the beginning
* add bloomz:2048 to exclude
2023-12-13 18:13:06 +08:00
Yuwen Hu
968d99e6f5
Remove empty cache between each iteration of generation ( #9660 )
2023-12-12 17:24:06 +08:00
Chen, Zhentao
972cdb9992
gsm8k OOM workaround ( #9597 )
...
* update bigdl_llm.py
* update the installation of harness
* fix partial function
* import ipex
* force seq len in decrease order
* put func outside class
* move comments
* default 'trust_remote_code' as True
* Update llm-harness-evaluation.yml
2023-12-08 18:47:25 +08:00
WeiguangHan
e9299adb3b
LLM: Highlight some values in the html ( #9635 )
...
* highlight some values in the html
* revert the llm_performance_tests.yml
2023-12-07 19:02:41 +08:00
Yuwen Hu
48b85593b3
Update all-in-one benchmark readme ( #9618 )
2023-12-07 10:32:09 +08:00
Yuwen Hu
0e8f4020e5
Add traceback error output for win igpu test api in benchmark ( #9607 )
2023-12-06 14:35:16 +08:00
Yuwen Hu
c998f5f2ba
[LLM] iGPU long context tests ( #9598 )
...
* Temp enable PR
* Enable tests for 256-64
* Try again 128-64
* Empty cache after each iteration for igpu benchmark scripts
* Try tests for 512
* change order for 512
* Skip chatglm3 and llama2 for now
* Separate tests for 512-64
* Small fix
* Further fixes
* Change back to nightly again
2023-12-06 10:19:20 +08:00
Chen, Zhentao
8c8a27ded7
Add harness summary job ( #9457 )
...
* format yml
* add make_table_results
* add summary job
* add a job to print single result
* upload full directory
2023-12-05 10:04:10 +08:00
Yuwen Hu
3f4ad97929
[LLM] Add performance tests for windows iGPU ( #9584 )
...
* Add support for win gpu benchmark with peak gpu memory monitoring
* Add win igpu tests
* Small fix
* Forward outputs
* Small fix
* Test and small fixes
* Small fix
* Small fix and test
* Small fixes
* Add tests for 512-64 and change back to nightly tests
* Small fix
2023-12-04 20:50:02 +08:00
Chen, Zhentao
cb228c70ea
Add harness nightly ( #9552 )
...
* modify output_path as a directory
* schedule nightly at 21 on Friday
* add tasks and models for nightly
* add accuracy regression
* comment out if to test
* mixed fp4
* for test
* add missing delimiter
* remove comma
* fixed golden results
* add mixed 4 golden result
* add more options
* add mistral results
* get golden result of stable lm
* move nightly scripts and results to test folder
* add license
* add fp8 stable lm golden
* run on all available devices
* trigger only when ready for review
* fix new line
* update golden
* add mistral
2023-12-01 14:16:35 +08:00
Chen, Zhentao
4d7d5d4c59
Add 3 leaderboard tasks ( #9566 )
...
* update leaderboard map
* download model and dataset without overwritten
* fix task drop
* run on all available devices
2023-12-01 14:01:14 +08:00
Chen, Zhentao
c8e0c2ed48
Fixed dumped logs in harness ( #9549 )
...
* install transformers==4.34.0
* modify output_path as a directory
* add device and task to output dir parents
2023-11-30 12:47:56 +08:00
Chen, Zhentao
45820cf3b9
add optimize model option ( #9530 )
2023-11-24 17:10:49 +08:00
Ruonan Wang
139e98aa18
LLM: quick fix benchmark ( #9509 )
2023-11-22 10:19:57 +08:00
WeiguangHan
c2aeb4d1e8
del model after test ( #9504 )
2023-11-21 18:41:50 +08:00
Cheen Hau, 俊豪
3e39828420
Update all in one benchmark readme ( #9496 )
...
* Add gperftools install to all in one benchmark readme
* Update readme
2023-11-21 14:57:16 +08:00
WeiguangHan
c487b53f21
LLM: only run arc perf test nightly ( #9448 )
...
* LLM: only run arc perf test nightly
* deleted unused python scripts
* rebase main
2023-11-15 19:38:14 +08:00
Chen, Zhentao
dbbdb53a18
fix multiple gpu usage ( #9459 )
2023-11-14 17:06:27 +08:00
Chen, Zhentao
d19ca21957
patch bigdl-llm model to harness by binding instead of patch file ( #9420 )
...
* add run_llb.py
* fix args interpret
* modify outputs
* update workflow
* add license
* test mixed 4 bit
* update readme
* use autotokenizer
* add timeout
* refactor workflow file
* fix working directory
* fix env
* throw exception if some jobs failed
* improve terminal outputs
* Disable var which cause the run stuck
* fix unknown precision
* fix key error
* directly output config instead
* rm harness submodule
2023-11-14 12:51:39 +08:00
Chen, Zhentao
0ecb9efb05
use AutoTokenizer to enable more models ( #9446 )
2023-11-13 17:47:43 +08:00
Cengguang Zhang
ece5805572
LLM: add chatglm3-6b to latency benchmark test. ( #9442 )
2023-11-13 17:24:37 +08:00
Chen, Zhentao
5747e2fe69
fix multiple gpu usage of harness ( #9444 )
2023-11-13 16:53:23 +08:00
Heyang Sun
b23b91407c
fix llm-init on deepspeed missing lib ( #9419 )
2023-11-10 13:51:24 +08:00
Chen, Zhentao
298b64217e
add auto triggered acc test ( #9364 )
...
* add auto triggered acc test
* use llama 7b instead
* fix env
* debug download
* fix download prefix
* add cut dirs
* fix env of model path
* fix dataset download
* full job
* source xpu env vars
* use matrix to trigger model run
* reset batch=1
* remove redirect
* remove some trigger
* add task matrix
* add precision list
* test llama-7b-chat
* use /mnt/disk1 to store model and datasets
* remove installation test
* correct downloading path
* fix HF vars
* add bigdl-llm env vars
* rename file
* fix hf_home
* fix script path
* rename as harness evalution
* rerun
2023-11-08 10:22:27 +08:00
WeiguangHan
84ab614aab
LLM: add more models and skip runtime error ( #9349 )
...
* add more models and skip runtime error
* upgrade transformers
* temporarily removed Mistral-7B-v0.1
* temporarily disable the upload of arc perf result
2023-11-08 09:45:53 +08:00
Heyang Sun
af94058203
[LLM] Support CPU deepspeed distributed inference ( #9259 )
...
* [LLM] Support CPU Deepspeed distributed inference
* Update run_deepspeed.py
* Rename
* fix style
* add new codes
* refine
* remove annotated codes
* refine
* Update README.md
* refine doc and example code
2023-11-06 17:56:42 +08:00
Chen, Zhentao
d4dffbdb62
Merge harness ( #9319 )
...
* add harness patch and llb script
* add readme
* add license
* use patch instead
* update readme
* rename tests to evaluation
* fix typo
* remove nano dependency
* add original harness link
* rename title of usage
* rename BigDLGPULM as BigDLLM
* empty commit to rerun job
2023-11-02 15:14:19 +08:00
Ruonan Wang
7e73c354a6
LLM: decoupling bigdl-llm and bigdl-nano ( #9306 )
2023-11-01 11:00:54 +08:00
binbin Deng
770ac70b00
LLM: add low_bit option in benchmark scripts ( #9257 )
2023-10-25 10:27:48 +08:00
WeiguangHan
ec9195da42
LLM: using html to visualize the perf result for Arc ( #9228 )
...
* LLM: using html to visualize the perf result for Arc
* deploy the html file
* add python license
* reslove some comments
2023-10-24 18:05:25 +08:00
Ruonan Wang
b15656229e
LLM: fix benchmark issue ( #9255 )
2023-10-24 14:15:05 +08:00
WeiguangHan
b9194c5786
LLM: skip some model tests using certain api ( #9163 )
...
* LLM: Skip some model tests using certain api
* initialize variable named result
2023-10-18 09:39:27 +08:00
Ruonan Wang
4f34557224
LLM: support num_beams in all-in-one benchmark ( #9141 )
...
* support num_beams
* fix
2023-10-12 13:35:12 +08:00
Ruonan Wang
62ac7ae444
LLM: fix inaccurate input / output tokens of current all-in-one benchmark ( #9137 )
...
* first fix
* fix all apis
* fix
2023-10-11 17:13:34 +08:00
Ruonan Wang
1c8d5da362
LLM: fix llama tokenizer for all-in-one benchmark ( #9129 )
...
* fix tokenizer for gpu benchmark
* fix ipex fp16
* meet code review
* fix
2023-10-11 13:39:39 +08:00
Ruonan Wang
1363e666fc
LLM: update benchmark_util.py for beam search ( #9126 )
...
* update reorder_cache
* fix
2023-10-11 09:41:53 +08:00
Ruonan Wang
ad7d9231f5
LLM: add benchmark script for Max gpu and ipex fp16 gpu ( #9112 )
...
* add pvc bash
* meet code review
* rename to run-max-gpu.sh
2023-10-10 10:18:41 +08:00
Yuwen Hu
65212451cc
[LLM] Small update to performance tests ( #9106 )
...
* small updates to llm performance tests regarding model handling
* Small fix
2023-10-09 16:55:25 +08:00
Kai Huang
78ea7ddb1c
Combine apply_rotary_pos_emb for gpt-neox ( #9074 )
2023-10-07 16:27:46 +08:00
Cengguang Zhang
ad62c58b33
LLM: Enable jemalloc in benchmark scripts. ( #9058 )
...
* enable jemalloc.
* fix readme.
2023-09-26 15:37:49 +08:00
Cengguang Zhang
26213a5829
LLM: Change benchmark bf16 load format. ( #9035 )
...
* LLM: Change benchmark bf16 load format.
* comment on bf16 chatglm.
* fix.
2023-09-22 17:38:38 +08:00
Kai Huang
6981745fe4
Optimize kv_cache for gpt-neox model family ( #9015 )
...
* override gptneox
* style
* move to utils
* revert
2023-09-20 19:59:19 +08:00
Xin Qiu
37bb0cbf8f
Speed up gpt-j in gpubenchmark ( #9000 )
...
* Speedup gpt-j in gpubenchmark
* meet code review
2023-09-19 14:22:28 +08:00
Cengguang Zhang
8299b68fea
update readme. ( #8996 )
2023-09-18 17:06:15 +08:00
Cengguang Zhang
74338fd291
LLM: add auto torch dtype in benchmark. ( #8981 )
2023-09-18 15:48:25 +08:00
Ruonan Wang
32716106e0
update use_cahce=True ( #8986 )
2023-09-18 07:59:33 +08:00
Xin Qiu
64ee1d7689
update run_transformer_int4_gpu ( #8983 )
...
* xpuperf
* update run.py
* clean upo
* uodate
* update
* meet code review
2023-09-15 15:10:04 +08:00
Cengguang Zhang
cca84b0a64
LLM: update llm benchmark scripts. ( #8943 )
...
* update llm benchmark scripts.
* change tranformer_bf16 to pytorch_autocast_bf16.
* add autocast in transformer int4.
* revert autocast.
* add "pytorch_autocast_bf16" to doc
* fix comments.
2023-09-13 12:23:28 +08:00
Xin Qiu
ea0853c0b5
update benchmark_utils readme ( #8925 )
...
* update readme
* meet code review
2023-09-08 10:30:26 +08:00
Cengguang Zhang
3d2efe9608
LLM: update llm latency benchmark. ( #8922 )
2023-09-07 19:00:19 +08:00
binbin Deng
7897eb4b51
LLM: add benchmark scripts on GPU ( #8916 )
2023-09-07 18:08:17 +08:00
Xin Qiu
d8a01d7c4f
fix chatglm in run.pu ( #8919 )
2023-09-07 16:44:10 +08:00
Xin Qiu
e9de9d9950
benchmark for native int4 ( #8918 )
...
* native4
* update
* update
* update
2023-09-07 15:56:15 +08:00
Ruonan Wang
057e77e229
LLM: update benchmark_utils.py to handle do_sample=True ( #8903 )
2023-09-07 14:20:47 +08:00
Xin Qiu
5d9942a3ca
transformer int4 and native int4's benchmark script for 32 256 1k 2k input ( #8871 )
...
* transformer
* move
* update
* add header
* update all-in-one
* clean up
2023-09-07 09:49:55 +08:00
Xin Qiu
49a39452c6
update benchmark ( #8899 )
2023-09-06 15:11:43 +08:00
Song Jiaming
7b3ac66e17
[LLM] auto performance test fix specific settings to template ( #8876 )
2023-09-01 15:49:04 +08:00
Song Jiaming
c06f1ca93e
[LLM] auto perf test to output to csv ( #8846 )
2023-09-01 10:48:00 +08:00
Song Jiaming
b8b1b6888b
[LLM] Performance test ( #8796 )
2023-08-25 14:31:45 +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
Ruonan Wang
8805186f2f
LLM: add benchmark tool for gpu ( #8760 )
...
* add benchmark tool for gpu
* update
2023-08-16 11:22:10 +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
