binbin Deng
3feb58d1e4
Support baichuan2 for level0 pipeline ( #12289 )
2024-10-29 19:24:16 +08:00
Zhao Changmin
546f455e8e
Patch sdpa check function in specific module attributes table ( #12285 )
2024-10-29 18:41:09 +08:00
Ruonan Wang
821b0033ed
[NPU L0] update layernorm & code refactor ( #12287 )
...
* update layernorm & code refactor
* fix style
* add common utils
* change to Pool()
* remove print
2024-10-29 15:01:45 +08:00
Yina Chen
4467645088
[NPU] Support l0 Llama groupwise ( #12276 )
...
* except lm_head
* remove
* support gw lm_head
* update
* fix
* remove run.bat
* fix style
* support llama3
2024-10-28 17:06:55 +08:00
Ruonan Wang
3fe2ea3081
[NPU] Reuse prefill of acc lib for pipeline ( #12279 )
...
* first commit
* update example
* fix style
* update example
* embedding as const
* fix generate
* code refactor
* meet code review
* fix style
* change max_output_len to max_context_len
* fix all-in-one
* fix example
* add check for new tokens
2024-10-28 16:05:49 +08:00
binbin Deng
ec362e6133
Add llama3 level0 example ( #12275 )
2024-10-28 09:24:51 +08:00
SONG Ge
08cb065370
hot-fix redundant import funasr ( #12277 )
2024-10-25 19:40:39 +08:00
SONG Ge
a0c6432899
[NPU] Add support for loading a FunASR model ( #12073 )
...
* add support for loading funasr model
* add initial support for paraformer-encoder
* add npu ops impl
* add encoder-decoder npu pipeline
* move paraformer encoders prefix 30 layers to npu and keep the rest layers on cpu
2024-10-25 17:22:01 +08:00
Ruonan Wang
854398f6e0
update example to reduce peak memory usage ( #12274 )
2024-10-25 17:09:26 +08:00
Yuwen Hu
e713296090
Update all-in-one benchmark ( #12272 )
...
* Update all-in-one benchmark
* Small fix
* Small fix
* Small fix
2024-10-25 16:52:59 +08:00
Yuwen Hu
43b25a2fe7
Fix llama 3.2 vision on LNL ( #12264 )
...
* Fix llama 3.2 vision on LNL
* Small fix
2024-10-25 16:23:31 +08:00
Yuwen Hu
93895b2ac2
Openvino all in one benchmark small fix ( #12269 )
...
* Small update for all-in-one benchmark readme to support OpenVINO tests
* Small fix
2024-10-25 14:13:52 +08:00
Zijie Li
f7f62a3fef
Add OpenVINO performance tests to all-in-one benchmark ( #12238 )
...
* add-openvino-to-all-in-one
* update on openvino API
* Update save_openvino.py
* Update save_openvino.py
* Update save_openvino.py
* update on run.py and save_openvino
* update references
* Create openvino-requirements.txt
* fix on comments
* Small updates
* Small fix
* Fix
---------
Co-authored-by: Yuwen Hu <yuwen.hu@intel.com>
2024-10-25 13:53:53 +08:00
Ruonan Wang
ae57e23e4f
fix incompatibility between llama GW & llama pipeline ( #12267 )
...
* fix
* fix
2024-10-25 10:31:44 +08:00
Yina Chen
b5e663854b
[NPU] Support llama groupwise ( #12260 )
...
* support llama gw
* support llama gw lm_head
* fix style
* remove unused code
2024-10-24 18:06:45 +08:00
Xin Qiu
39c9d1de52
fix code geex ( #12261 )
2024-10-24 14:34:01 +08:00
Yishuo Wang
f3a2b20e6b
Optimize gpt2 ( #12259 )
2024-10-24 13:44:24 +08:00
Ruonan Wang
821fd96367
Initial integrate our L0 Llama impl into ipex-llm ( #12255 )
...
* temp save
* initial support
* fix
* simplify code
* fix style
* fix example
* make default value of pipeline as False
2024-10-24 09:49:27 +08:00
Yishuo Wang
cacc891962
Fix PR validation ( #12253 )
2024-10-23 18:10:47 +08:00
binbin Deng
b685cf4349
Fix npu group size setting of optimize_model=False ( #12256 )
2024-10-23 17:53:54 +08:00
binbin Deng
567b77a76b
Support IR and blob format for llama level0 pipeline ( #12251 )
2024-10-23 16:02:35 +08:00
Yishuo Wang
578aef245d
Fix models auto choose SdpaAttention with ipex 2.3 ( #12252 )
2024-10-23 15:33:45 +08:00
Yishuo Wang
88dc120a4c
fix fp16 linear ( #12250 )
2024-10-23 14:35:19 +08:00
Yina Chen
e8cf7f32f5
npu gw small fix ( #12249 )
2024-10-23 14:26:01 +08:00
Shaojun Liu
aae2490cb8
fix UT ( #12247 )
...
* fix ut
* Update test_transformers_api_attention.py
* Update test_transformers_api_mlp.py
2024-10-23 14:13:06 +08:00
Yina Chen
e37f951cce
[NPU] Groupwise ( #12241 )
...
* dq divide
* fix
* support attn divide
* update qwen2 7b
* divide down_proj & other linear
* use concat & reduce sum
* support scale after
* support qwen2
* w/ mm
* update reshape
* spda
* split
* split 2+
* update
* lm head-> 28
* no scale
* update
* update
* update
* fix style
* fix style
* to split linear
* update
* update code
* address comments
* fix style & remove redundant code & revert benchmark scripts
* fix style & remove code
* update save & load
---------
Co-authored-by: Yang Wang <yang3.wang@intel.com>
2024-10-23 14:10:58 +08:00
Jin, Qiao
8fa98e2742
Remove Qwen2-7b from NPU example for "Run Optimized Models (Experimental)" ( #12245 )
...
* Remove qwen2-7b from npu example readme
* fix
2024-10-22 17:07:51 +08:00
Yina Chen
ec465fbcd7
Add lookup generate in load_low_bit ( #12243 )
...
* add lookup generate in load_low_bit
* update comment
2024-10-22 15:51:52 +08:00
Yuwen Hu
b3df47486d
Fix Gemma 2 on LNL ( #12240 )
...
* Fix gemma 2 on LNL
* Python style fix
2024-10-21 18:25:53 +08:00
Yuwen Hu
5935b25622
Further update windows gpu perf test regarding results integrity check ( #12232 )
2024-10-18 18:15:13 +08:00
Yuwen Hu
b88c1df324
Add Llama 3.1 & 3.2 to Arc Performance test ( #12225 )
...
* Add llama3.1 and llama3.2 in arc perf (#12202 )
* Add llama3.1 and llama3.2 in arc perf
* Uninstall trl after arc test on transformers>=4.40
* Fix arc llama3 perf (#12212 )
* Fix pip uninstall
* Uninstall trl after test on transformers==4.43.1
* Fix llama3 arc perf (#12218 )
---------
Co-authored-by: Jin, Qiao <89779290+JinBridger@users.noreply.github.com>
2024-10-17 21:12:45 +08:00
Yishuo Wang
9ea694484d
refactor ot remove old rope usage ( #12224 )
2024-10-17 17:06:09 +08:00
Yishuo Wang
324bcb057e
refactor to reduce old rope usage ( #12219 )
2024-10-17 14:45:09 +08:00
Jiao Wang
667f0db466
Update Eagle example to Eagle2+ipex-llm integration ( #11717 )
...
* update to e2 example
* update
* update
2024-10-16 23:16:14 -07:00
Yishuo Wang
a4a758656a
refactor gemma to reduce old fuse rope usage ( #12215 )
2024-10-16 17:40:28 +08:00
Yishuo Wang
9104a168f6
refactor phi-2 to reduce old fuse rope usage ( #12214 )
2024-10-16 17:08:14 +08:00
Yishuo Wang
bb247e991b
refactor merge_qkv and attention_softmax ( #12213 )
2024-10-16 15:58:14 +08:00
Yishuo Wang
e279148aa0
optimize llama3.2 vision again ( #12211 )
2024-10-16 14:29:48 +08:00
Chu,Youcheng
f17cc4fdee
feat: add llama3.2-11b-vision in all in one ( #12207 )
...
* feat: add llama3.2-11b-vision in all in one
* fix: change model
* fix: change name
* fix: add a space
* fix: switch import
2024-10-16 10:32:11 +08:00
Yuwen Hu
c9ac39fc1e
Add Llama 3.2 to iGPU performance test (transformers 4.45) ( #12209 )
...
* Add Llama 3.2 to iGPU Perf (#12200 )
* Add Llama 3.2 to iGPU Perf
* Downgrade accelerate after step
* Temporarily disable model for test
* Temporarily change ERRORLEVEL check (#12201 )
* Restore llama3.2 perf (#12206 )
* Revert "Temporarily change ERRORLEVEL check"
This reverts commit 909dbbc930ab4283737161a55bb32006e6ca1991.
* Revert "Temporarily disable model for test"
This reverts commit 95322dc3c6429aa836f21bda0b5ba8d9b48592f8.
---------
Co-authored-by: Jin, Qiao <89779290+JinBridger@users.noreply.github.com>
2024-10-15 17:44:46 +08:00
Yishuo Wang
f6611f9d3a
optimize llama3.2 vison attention again ( #12204 )
2024-10-15 16:08:20 +08:00
Yishuo Wang
9b81236a2e
optimzie qwen2-vl vision ( #12203 )
2024-10-15 15:54:25 +08:00
Yishuo Wang
d5344587ab
optimize internvl2 vision model's attention ( #12198 )
2024-10-15 10:51:00 +08:00
Yuwen Hu
f8d1adc573
Fix Llama 3.2 & 3.1 on LNL ( #12196 )
2024-10-14 17:39:20 +08:00
Yuwen Hu
516b578104
Support cpp release for ARL on Windows ( #12189 )
...
* Support cpp Windows release for ARL
* Temp commit for test
* Remove temp commit
2024-10-14 17:20:31 +08:00
Zijie Li
7d80db710e
Add benchmark_util for transformers >= 4.44.0 ( #12171 )
...
* Create benchmark_util_4_45.py
* Update __init__.py
* Update lint-python
* Update benchmark_util_4_45.py
* Update benchmark_util_4_45.py
* Create benchmark_util_4_44.py
2024-10-14 15:40:12 +08:00
Jin, Qiao
8e35800abe
Add llama 3.1 in igpu perf ( #12194 )
2024-10-14 15:14:34 +08:00
Yuwen Hu
ddcdf47539
Support Windows ARL release ( #12183 )
...
* Support release for ARL
* Small fix
* Small fix to doc
* Temp for test
* Remove temp commit for test
2024-10-11 18:30:52 +08:00
Jinhe
f983f1a8f4
Add Qwen2-VL gpu example ( #12135 )
...
* qwen2-vl readme
* add qwen2-vl example
* fix
* fix
* fix
* add link
* Update regarding modules_to_not_convert and readme
* Further fix
* Small fix
---------
Co-authored-by: Yuwen Hu <yuwen.hu@intel.com>
2024-10-11 18:25:23 +08:00
Ruonan Wang
310f18c8af
update NPU pipeline generate ( #12182 )
...
* update
* fix style
2024-10-11 17:39:20 +08:00
Shaojun Liu
724b2ae66d
add npu-level0 pipeline.dll to ipex-llm ( #12181 )
...
* add npu-level0 pipeline.dll to ipex-llm
* test
* update runner label
* fix
* update
* fix
* fix
2024-10-11 16:05:20 +08:00
Ruonan Wang
4d93bb81fe
Initial support of NPU level0 Model ( #12177 )
...
* first commit to support load dll and init llm pipeline
* add init generate
* fix style
* small updates
* fix style and check tokens number
2024-10-11 09:45:53 +08:00
Yuwen Hu
890662610b
Fix auto importer for LNL release ( #12175 )
2024-10-10 15:17:43 +08:00
Yishuo Wang
535bee5381
fix qwen2 vl again ( #12174 )
2024-10-10 13:50:01 +08:00
Yuwen Hu
aef1f671bd
Support LNL Windows release ( #12169 )
...
* Release for LNL on Windows
* Temp commit for release test
* Change option name
* Remove temp commit and change option name
* temp commit for test again
* Remove temp commit
2024-10-09 17:41:10 +08:00
Yishuo Wang
78d253165d
optimize qwen2 vl perf again ( #12167 )
2024-10-09 16:43:48 +08:00
Zijie Li
3d044dbf53
add llama3.2-vision Pytorch example ( #12165 )
2024-10-09 09:20:42 +08:00
Yishuo Wang
644af2a76e
add basic llama 3.2 vision support ( #12163 )
2024-10-08 10:46:48 +08:00
Ch1y0q
17c23cd759
add llama3.2 GPU example ( #12137 )
...
* add llama3.2 GPU example
* change prompt format reference url
* update
* add Meta-Llama-3.2-1B-Instruct sample output
* update wording
2024-09-29 14:41:54 +08:00
Yuwen Hu
f71b38a994
Update MiniCPM_V_26 GPU example with save & load ( #12127 )
2024-09-26 17:40:22 +08:00
Yishuo Wang
669ff1a97b
fix sd1.5 ( #12129 )
2024-09-26 17:15:16 +08:00
Yishuo Wang
a266528719
optimize llama 3.2 rope ( #12128 )
2024-09-26 16:08:10 +08:00
Yishuo Wang
584c3489e7
add basic support for llama3.2 ( #12125 )
2024-09-26 15:46:19 +08:00
Yishuo Wang
66f419f8b7
fix qwen2 vl ( #12126 )
2024-09-26 15:44:02 +08:00
Ch1y0q
2ea13d502f
Add minicpm3 gpu example ( #12114 )
...
* add minicpm3 gpu example
* update GPU example
* update
---------
Co-authored-by: Huang, Xinshengzi <xinshengzi.huang@intel.com>
2024-09-26 13:51:37 +08:00
Yishuo Wang
77af9bc5fa
support passing None to low_bit in optimize_model ( #12121 )
2024-09-26 11:09:35 +08:00
Yishuo Wang
47e0b83cbf
optimize sd 1.5 ( #12119 )
2024-09-25 15:45:13 +08:00
Jin, Qiao
2bedb17be7
Add Qwen2.5 NPU Example ( #12110 )
...
* Add Qwen2.5 NPU Example
* fix
* Merge qwen2.py and qwen2.5.py into qwen.py
* Fix description
2024-09-25 15:20:03 +08:00
Yishuo Wang
5d63aef60b
optimize qwen2 vl again ( #12109 )
2024-09-23 13:22:01 +08:00
Ruonan Wang
03bd01c99c
optimize npu qwen2 ( #12107 )
2024-09-20 19:46:16 +08:00
Jinhe
02399021d6
add npu load_low_bit api in all-in-one benchmark ( #12103 )
2024-09-20 17:56:08 +08:00
Yishuo Wang
9239fd4f12
add basic support and optimization for qwen2-vl ( #12104 )
2024-09-20 17:23:06 +08:00
Yuwen Hu
828fa01ad3
[NPU] Add mixed_precision for Qwen2 7B ( #12098 )
...
* Add mix_precision argument to control whether use INT8 lm_head for Qwen2-7B-Instruct
* Small fix
* Fixed on load low bit with mixed precision
* Small fix
* Update example accordingly
* Update for default prompt
* Update base on comments
* Final fix
2024-09-20 16:36:21 +08:00
Ch1y0q
2269768e71
add internvl2 example ( #12102 )
...
* add internvl2 example
* add to README.md
* update
* add link to zh-CN readme
2024-09-20 16:31:54 +08:00
Ruonan Wang
09b8c80d9d
update code for NPU qwen2 ( #12094 )
...
* update code
* fix
2024-09-20 15:58:32 +08:00
Jin, Qiao
db7500bfd4
Add Qwen2.5 GPU example ( #12101 )
...
* Add Qwen2.5 GPU example
* fix end line
* fix description
2024-09-20 15:55:57 +08:00
Yishuo Wang
54b973c744
fix ipex_llm import in transformers 4.45 ( #12099 )
2024-09-20 15:24:59 +08:00
Ch1y0q
9650bf616a
add transpose_value_cache for NPU benchmark ( #12092 )
...
* add `transpose_value_cache`
* update
* update
2024-09-19 18:45:05 +08:00
Yuwen Hu
f7fb3c896c
Update lm_head optimization for Qwen2 7B ( #12090 )
2024-09-18 17:02:02 +08:00
Xu, Shuo
ee33b93464
Longbench: NV code to ipex-llm ( #11662 )
...
* add nv longbench
* LongBench: NV code to ipex-llm
* ammend
* add more models support
* ammend
* optimize LongBench's user experience
* ammend
* ammend
* fix typo
* ammend
* remove cuda related information & add a readme
* add license to python scripts & polish the readme
* ammend
* ammend
---------
Co-authored-by: cyita <yitastudy@gmail.com>
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
Co-authored-by: leonardozcm <leonardo1997zcm@gmail.com>
2024-09-18 15:55:14 +08:00
Wang, Jian4
40e463c66b
Enable vllm load gptq model ( #12083 )
...
* enable vllm load gptq model
* update
* update
* update
* update style
2024-09-18 14:41:00 +08:00
Ruonan Wang
081af41def
[NPU] Optimize Qwen2 lm_head to use INT4 ( #12072 )
...
* temp save
* update
* fix
* fix
* Split lm_head into 7 parts & remove int8 for lm_head when sym_int4
* Simlify and add condition to code
* Small fix
* refactor some code
* fix style
* fix style
* fix style
* fix
* fix
* temp sav e
* refactor
* fix style
* further refactor
* simplify code
* meet code review
* fix style
---------
Co-authored-by: Yuwen Hu <yuwen.hu@intel.com>
2024-09-14 15:26:46 +08:00
Ch1y0q
b4b8c3e495
add lowbit_path for generate.py, fix npu_model ( #12077 )
...
* add `lowbit_path` for `generate.py`, fix `npu_model`
* update `README.md`
2024-09-13 17:28:05 +08:00
Wang, Jian4
d703e4f127
Enable vllm multimodal minicpm-v-2-6 ( #12074 )
...
* enable minicpm-v-2-6
* add image_url readme
2024-09-13 13:28:35 +08:00
Ruonan Wang
48d9092b5a
upgrade OneAPI version for cpp Windows ( #12063 )
...
* update version
* update quickstart
2024-09-12 11:12:12 +08:00
Jinhe
e78e45ee01
update NPU readme: run conhost as administrator ( #12066 )
2024-09-11 17:54:04 +08:00
Jinhe
4ca330da15
Fix NPU load error message and add minicpm npu lowbit feat ( #12064 )
...
* fix npu_model raise sym_int4 error
* add load_lowbit
* remove print&perf
2024-09-11 16:56:35 +08:00
Jinhe
32e8362da7
added minicpm cpu examples ( #12027 )
...
* minicpm cpu examples
* add link for minicpm-2
2024-09-11 15:51:21 +08:00
Ruonan Wang
a0c73c26d8
clean NPU code ( #12060 )
...
* clean code
* remove time.perf_counter()
2024-09-11 15:10:35 +08:00
Wang, Jian4
c75f3dd874
vllm no padding glm4 to avoid nan error ( #12062 )
...
* no padding glm4
* add codegeex
2024-09-11 13:44:40 +08:00
Chu,Youcheng
649390c464
fix: textual and env variable adjustment ( #12038 )
2024-09-11 13:38:01 +08:00
Wang, Jian4
30a8680645
Update for vllm one card padding ( #12058 )
2024-09-11 10:52:55 +08:00
Zijie Li
c5fdfde1bd
fix npu-model prompt ( #12057 )
2024-09-11 10:06:45 +08:00
Yishuo Wang
d8c044e79d
optimize minicpm3 kv cache ( #12052 )
2024-09-10 16:51:21 +08:00
Wang, Jian4
5d3ab16a80
Add vllm glm and baichuan padding ( #12053 )
2024-09-10 15:57:28 +08:00
Guancheng Fu
69c8d36f16
Switching from vLLM v0.3.3 to vLLM 0.5.4 ( #12042 )
...
* Enable single card sync engine
* enable ipex-llm optimizations for vllm
* enable optimizations for lm_head
* Fix chatglm multi-reference problem
* Remove duplicate layer
* LLM: Update vLLM to v0.5.4 (#11746 )
* Enable single card sync engine
* enable ipex-llm optimizations for vllm
* enable optimizations for lm_head
* Fix chatglm multi-reference problem
* update 0.5.4 api_server
* add dockerfile
* fix
* fix
* refine
* fix
---------
Co-authored-by: gc-fu <guancheng.fu@intel.com>
* Add vllm-0.5.4 Dockerfile (#11838 )
* Update BIGDL_LLM_SDP_IGNORE_MASK in start-vllm-service.sh (#11957 )
* Fix vLLM not convert issues (#11817 ) (#11918 )
* Fix not convert issues
* refine
Co-authored-by: Guancheng Fu <110874468+gc-fu@users.noreply.github.com>
* Fix glm4-9b-chat nan error on vllm 0.5.4 (#11969 )
* init
* update mlp forward
* fix minicpm error in vllm 0.5.4
* fix dependabot alerts (#12008 )
* Update 0.5.4 dockerfile (#12021 )
* Add vllm awq loading logic (#11987 )
* [ADD] Add vllm awq loading logic
* [FIX] fix the module.linear_method path
* [FIX] fix quant_config path error
* Enable Qwen padding mlp to 256 to support batch_forward (#12030 )
* Enable padding mlp
* padding to 256
* update style
* Install 27191 runtime in 0.5.4 docker image (#12040 )
* fix rebase error
* fix rebase error
* vLLM: format for 0.5.4 rebase (#12043 )
* format
* Update model_convert.py
* Fix serving docker related modifications (#12046 )
* Fix undesired modifications (#12048 )
* fix
* Refine offline_inference arguments
---------
Co-authored-by: Xiangyu Tian <109123695+xiangyuT@users.noreply.github.com>
Co-authored-by: Jun Wang <thoughts.times@gmail.com>
Co-authored-by: Wang, Jian4 <61138589+hzjane@users.noreply.github.com>
Co-authored-by: liu-shaojun <johnssalyn@outlook.com>
Co-authored-by: Shaojun Liu <61072813+liu-shaojun@users.noreply.github.com>
2024-09-10 15:37:43 +08:00
Ch1y0q
73a4360f3f
update lowbit path for baichuan2, qwen2, generate.py ( #12051 )
...
* update lowbit path for baichuan2, qwen2, `generate.py`
* update readme
2024-09-10 15:35:24 +08:00
Ruonan Wang
dc4af02b2a
Fix qwen2 1.5B NPU load error ( #12049 )
2024-09-10 14:41:18 +08:00
Yishuo Wang
abc370728c
optimize minicpm3 again ( #12047 )
2024-09-10 14:19:57 +08:00
Ch1y0q
f0061a9916
remove local import os to fix Baichuan NPU load issue ( #12044 )
2024-09-10 14:13:24 +08:00
