Wang, Jian4
9c15abf825
Refactor fastapi-serving and add one card serving( #11581 )
...
* init fastapi-serving one card
* mv api code to source
* update worker
* update for style-check
* add worker
* update bash
* update
* update worker name and add readme
* rename update
* rename to fastapi
2024-07-17 11:12:43 +08:00
Yishuo Wang
5837bc0014
fix chatglm3 npu output ( #11590 )
2024-07-16 18:16:30 +08:00
Guancheng Fu
06930ab258
Enable ipex-llm optimization for lm head ( #11589 )
...
* basic
* Modify convert.py
* fix
2024-07-16 16:48:44 +08:00
Heyang Sun
365adad59f
Support LoRA ChatGLM with Alpaca Dataset ( #11580 )
...
* Support LoRA ChatGLM with Alpaca Dataset
* refine
* fix
* add 2-card alpaca
2024-07-16 15:40:02 +08:00
Yina Chen
99c22745b2
fix qwen 14b fp6 abnormal output ( #11583 )
2024-07-16 10:59:00 +08:00
Yishuo Wang
c279849d27
add disk embedding api ( #11585 )
2024-07-16 10:43:39 +08:00
Xiangyu Tian
79c742dfd5
LLM: Add XPU Memory Optimizations for Pipeline Parallel ( #11567 )
...
Add XPU Memory Optimizations for Pipeline Parallel
2024-07-16 09:44:50 +08:00
Ch1y0q
50cf563a71
Add example: MiniCPM-V ( #11570 )
2024-07-15 10:55:48 +08:00
Zhao Changmin
06745e5742
Add npu benchmark all-in-one script ( #11571 )
...
* npu benchmark
2024-07-15 10:42:37 +08:00
Yishuo Wang
019da6c0ab
use mlp silu_mul fusion in qwen2 to optimize memory usage ( #11574 )
2024-07-13 16:32:54 +08:00
Xu, Shuo
13a72dc51d
Test MiniCPM performance on iGPU in a more stable way ( #11573 )
...
* Test MiniCPM performance on iGPU in a more stable way
* small fix
---------
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
2024-07-12 17:07:41 +08:00
Xiangyu Tian
0981b72275
Fix /generate_stream api in Pipeline Parallel FastAPI ( #11569 )
2024-07-12 13:19:42 +08:00
Yishuo Wang
a945500a98
fix internlm xcomposser stream chat ( #11564 )
2024-07-11 18:21:17 +08:00
Zhao Changmin
b9c66994a5
add npu sdp ( #11562 )
2024-07-11 16:57:35 +08:00
binbin Deng
2b8ad8731e
Support pipeline parallel for glm-4v ( #11545 )
2024-07-11 16:06:06 +08:00
Xiangyu Tian
7f5111a998
LLM: Refine start script for Pipeline Parallel Serving ( #11557 )
...
Refine start script and readme for Pipeline Parallel Serving
2024-07-11 15:45:27 +08:00
Xu, Shuo
1355b2ce06
Add model Qwen-VL-Chat to iGPU-perf ( #11558 )
...
* Add model Qwen-VL-Chat to iGPU-perf
* small fix
---------
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
2024-07-11 15:39:02 +08:00
Zhao Changmin
105e124752
optimize phi3-v encoder npu performance and add multimodal example ( #11553 )
...
* phi3-v
* readme
2024-07-11 13:59:14 +08:00
Cengguang Zhang
70ab1a6f1a
LLM: unify memory optimization env variables. ( #11549 )
...
* LLM: unify memory optimization env variables.
* fix comments.
2024-07-11 11:01:28 +08:00
Xu, Shuo
028ad4f63c
Add model phi-3-vision-128k-instruct to iGPU-perf benchmark ( #11554 )
...
* try to improve MIniCPM performance
* Add model phi-3-vision-128k-instruct to iGPU-perf benchmark
---------
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
2024-07-10 17:26:30 +08:00
Yishuo Wang
994e49a510
optimize internlm xcomposser performance again ( #11551 )
2024-07-10 17:08:56 +08:00
Xu, Shuo
61613b210c
try to improve MIniCPM performance ( #11552 )
...
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
2024-07-10 16:58:23 +08:00
Yishuo Wang
82f9514303
optimize internlm xcomposer2 performance ( #11550 )
2024-07-10 15:57:04 +08:00
Zhao Changmin
3c16c9f725
Optimize baichuan on NPU ( #11548 )
...
* baichuan_npu
2024-07-10 13:18:48 +08:00
Yuwen Hu
8982ab73d5
Add Yi-6B and StableLM to iGPU perf test ( #11546 )
...
* Add transformer4.38.2 test to igpu benchmark (#11529 )
* add transformer4.38.1 test to igpu benchmark
* use transformers4.38.2 & fix csv name error in 4.38 workflow
* add model Yi-6B-Chat & remove temporarily most models
---------
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
* filter some errorlevel (#11541 )
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
* Restore the temporarily removed models in iGPU-perf (#11544 )
* filter some errorlevel
* restore the temporarily removed models in iGPU-perf
---------
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
---------
Co-authored-by: Xu, Shuo <100334393+ATMxsp01@users.noreply.github.com>
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
2024-07-09 18:51:23 +08:00
Yishuo Wang
7dc6756d86
add disk embedding ( #11543 )
2024-07-09 17:38:40 +08:00
Zhao Changmin
76a5802acf
update NPU examples ( #11540 )
...
* update NPU examples
2024-07-09 17:19:42 +08:00
Yishuo Wang
99b2802d3b
optimize qewn2 memory ( #11535 )
2024-07-09 17:14:01 +08:00
Yishuo Wang
2929eb262e
support npu glm4 ( #11539 )
2024-07-09 15:46:49 +08:00
Xiangyu Tian
a1cede926d
Fix update_kv_cache in Pipeline-Parallel-Serving for glm4-9b model ( #11537 )
2024-07-09 14:08:04 +08:00
Cengguang Zhang
fa81dbefd3
LLM: update multi gpu write csv in all-in-one benchmark. ( #11538 )
2024-07-09 11:14:17 +08:00
Xin Qiu
69701b3ec8
fix typo in python/llm/scripts/README.md ( #11536 )
2024-07-09 09:53:14 +08:00
Jason Dai
099486afb7
Update README.md ( #11530 )
2024-07-08 20:18:41 +08:00
binbin Deng
66f6ffe4b2
Update GPU HF-Transformers example structure ( #11526 )
2024-07-08 17:58:06 +08:00
Xu, Shuo
f9a199900d
add model RWKV/v5-Eagle-7B-HF to igpu benchmark ( #11528 )
...
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
2024-07-08 15:50:16 +08:00
Shaojun Liu
9b37ca6027
remove ( #11527 )
2024-07-08 15:49:52 +08:00
Yishuo Wang
c26651f91f
add mistral npu support ( #11523 )
2024-07-08 13:17:15 +08:00
Jun Wang
5a57e54400
[ADD] add 5 new models for igpu-perf ( #11524 )
2024-07-08 11:12:15 +08:00
Xu, Shuo
64cfed602d
Add new models to benchmark ( #11505 )
...
* Add new models to benchmark
* remove Qwen/Qwen-VL-Chat to pass the validation
---------
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
2024-07-08 10:35:55 +08:00
binbin Deng
252426793b
Fix setting of use_quantize_kv_cache on different GPU in pipeline parallel ( #11516 )
2024-07-08 09:27:01 +08:00
Yishuo Wang
7cb09a8eac
optimize qwen2 memory usage again ( #11520 )
2024-07-05 17:32:34 +08:00
Yuwen Hu
8f376e5192
Change igpu perf to mainly test int4+fp16 ( #11513 )
2024-07-05 17:12:33 +08:00
Jun Wang
1efb6ebe93
[ADD] add transformer_int4_fp16_loadlowbit_gpu_win api ( #11511 )
...
* [ADD] add transformer_int4_fp16_loadlowbit_gpu_win api
* [UPDATE] add int4_fp16_lowbit config and description
* [FIX] fix run.py mistake
* [FIX] fix run.py mistake
* [FIX] fix indent; change dtype=float16 to model.half()
2024-07-05 16:38:41 +08:00
Zhao Changmin
f7e957aaf9
Clean npu dtype branch ( #11515 )
...
* clean branch
* create_npu_kernels
2024-07-05 15:45:26 +08:00
Yishuo Wang
14ce058004
add chatglm3 npu support ( #11518 )
2024-07-05 15:31:27 +08:00
Xin Qiu
a31f2cbe13
update minicpm.py ( #11517 )
...
* update minicpm
* meet code review
2024-07-05 15:25:44 +08:00
Zhao Changmin
24de13fc45
Optimize stablelm on NPU ( #11512 )
...
* stablelm_optimize
2024-07-05 14:21:57 +08:00
Xiangyu Tian
7d8bc83415
LLM: Partial Prefilling for Pipeline Parallel Serving ( #11457 )
...
LLM: Partial Prefilling for Pipeline Parallel Serving
2024-07-05 13:10:35 +08:00
binbin Deng
60de428b37
Support pipeline parallel for qwen-vl ( #11503 )
2024-07-04 18:03:57 +08:00
Zhao Changmin
57b8adb189
[WIP] Support npu load_low_bit method ( #11502 )
...
* npu_load_low_bit
2024-07-04 17:15:34 +08:00
Jun Wang
f07937945f
[REMOVE] remove all useless repo-id in benchmark/igpu-perf ( #11508 )
2024-07-04 16:38:34 +08:00
Yishuo Wang
1a8bab172e
add minicpm 1B/2B npu support ( #11507 )
2024-07-04 16:31:04 +08:00
Yishuo Wang
bb0a84044b
add qwen2 npu support ( #11504 )
2024-07-04 11:01:25 +08:00
Xin Qiu
f84ca99b9f
optimize gemma2 rmsnorm ( #11500 )
2024-07-03 15:21:03 +08:00
Wang, Jian4
61c36ba085
Add pp_serving verified models ( #11498 )
...
* add verified models
* update
* verify large model
* update commend
2024-07-03 14:57:09 +08:00
binbin Deng
9274282ef7
Support pipeline parallel for glm-4-9b-chat ( #11463 )
2024-07-03 14:25:28 +08:00
Yishuo Wang
d97c2664ce
use new fuse rope in stablelm family ( #11497 )
2024-07-03 11:08:26 +08:00
Xu, Shuo
52519e07df
remove models we no longer need in benchmark. ( #11492 )
...
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
2024-07-02 17:20:48 +08:00
Zhao Changmin
6a0134a9b2
support q4_0_rtn ( #11477 )
...
* q4_0_rtn
2024-07-02 16:57:02 +08:00
Yishuo Wang
5e967205ac
remove the code converts input to fp16 before calling batch forward kernel ( #11489 )
2024-07-02 16:23:53 +08:00
Wang, Jian4
4390e7dc49
Fix codegeex2 transformers version ( #11487 )
2024-07-02 15:09:28 +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
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
Xiangyu Tian
fd933c92d8
Fix: Correct num_requests in benchmark for Pipeline Parallel Serving ( #11462 )
2024-06-28 16:10:51 +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
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
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
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
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
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
Xiangyu Tian
b30bf7648e
Fix vLLM CPU api_server params ( #11384 )
2024-06-21 13:00:06 +08:00
ivy-lv11
21fc781fce
Add GLM-4V example ( #11343 )
...
* add example
* modify
* modify
* add line
* add
* add link and replace with phi-3-vision template
* fix generate options
* fix
* fix
---------
Co-authored-by: jinbridge <2635480475@qq.com>
2024-06-21 12:54:31 +08:00
binbin Deng
4ba82191f2
Support PP inference for chatglm3 ( #11375 )
2024-06-21 09:59:01 +08:00
Yishuo Wang
f0fdfa081b
Optimize qwen 1.5 14B batch performance ( #11370 )
2024-06-20 17:23:39 +08:00
Wenjing Margaret Mao
c0e86c523a
Add qwen-moe batch1 to nightly perf ( #11369 )
...
* add moe
* reduce 437 models
* rename
* fix syntax
* add moe check result
* add 430 + 437
* all modes
* 4-37-4 exclud
* revert & comment
---------
Co-authored-by: Yishuo Wang <yishuo.wang@intel.com>
2024-06-20 14:17:41 +08:00
Yishuo Wang
a5e7d93242
Add initial save/load low bit support for NPU(now only fp16 is supported) ( #11359 )
2024-06-20 10:49:39 +08:00
