Ruonan Wang
24b46b2b19
[NPU] further fix of qwen2 int8 pipeline & C++ ( #12449 )
...
* fix
* fix style
2024-11-26 16:39:39 +08:00
Yuwen Hu
303b104c10
Fix abnormal output for Qwen2-7B when sym_int8 ( #12446 )
2024-11-26 15:53:04 +08:00
Pepijn de Vos
71e1f11aa6
update serving image runtime ( #12433 )
2024-11-26 14:55:30 +08:00
Ruonan Wang
52c17fe104
Optimize first token of C++ NPU by adding npu_dpu_groups ( #12443 )
...
* add npu_dpu_groups
* add check for env
* fix style
2024-11-26 11:41:32 +08:00
Jinhe
66bd7abae4
add sdxl and lora-lcm optimization ( #12444 )
...
* add sdxl and lora-lcm optimization
* fix openjourney speed drop
2024-11-26 11:38:09 +08:00
Ruonan Wang
0e23bd779f
Add support of llama3.2 for NPU C++ ( #12442 )
...
* initial support of llama3.2
* update
* update
* fix style
* fix style
* fix
* small fix
2024-11-26 09:26:55 +08:00
Yishuo Wang
cdd41f5e4c
optimize sdxl again ( #12441 )
2024-11-25 17:46:46 +08:00
Ruonan Wang
b9abb8a285
Support qwen2.5 3B for NPU & update related examples ( #12438 )
...
* update qwen2.5-3B
* update convert
* small fix
* replace load_in_low_bit with low_bit
* small fix
2024-11-25 16:38:31 +08:00
Jinhe
b633fbf26c
add chinese prompt troubleshooting for npu cpp examples ( #12437 )
...
* add chinese prompt troubleshooting
* add chinese prompt troubleshooting
2024-11-25 15:28:47 +08:00
Yishuo Wang
8164aed802
small change ( #12439 )
2024-11-25 14:35:49 +08:00
Yishuo Wang
be132c4209
fix and optimize sd ( #12436 )
2024-11-25 14:09:48 +08:00
Ruonan Wang
f41405368a
Support minicpm for NPU C++ ( #12434 )
...
* support minicpm-1b
* update
* tune fused_layers
* update readme.md
2024-11-25 10:42:02 +08:00
Ruonan Wang
0819fad34e
support Llama2-7B / Llama3-8B for NPU C++ ( #12431 )
...
* support llama2
* update
* support fused_layers=4 for Llama2-7B
2024-11-22 18:47:19 +08:00
Ruonan Wang
4ffa6c752c
New convert support for C++ NPU ( #12430 )
...
* initial commit
* fix
* fix style
* fix style
* fix
* fix
2024-11-22 14:28:30 +08:00
Shaojun Liu
c089b6c10d
Update english prompt to 34k ( #12429 )
2024-11-22 11:20:35 +08:00
Yuwen Hu
e61ae88c5b
Upgrade denpendency for xpu_lnl and xpu_arl option ( #12424 )
2024-11-21 18:37:15 +08:00
Ruonan Wang
2935e97610
small fix of cpp readme( #12425 )
2024-11-21 18:21:34 +08:00
Yuwen Hu
8fdc36c140
Optimize with new batch kernel when batch_size=1 on LNL ( #12419 )
...
* Add use batch kernel condition for LNL
* Fix for other device judgement
* Fix based on comment
2024-11-21 16:21:35 +08:00
Jinhe
7e0a840f74
add optimization to openjourney ( #12423 )
...
* add optimization to openjourney
* add optimization to openjourney
2024-11-21 15:23:51 +08:00
Yishuo Wang
145e8b480f
update batch kernel condition ( #12421 )
2024-11-21 10:12:46 +08:00
Ruonan Wang
7288c759ce
Initial NPU C++ Example ( #12417 )
...
* temp save
* meet review, update
* update
* meet review, add license
* typo
2024-11-21 10:09:26 +08:00
Jinhe
d2a37b6ab2
add Stable diffusion examples ( #12418 )
...
* add openjourney example
* add timing
* add stable diffusion to model page
* 4.1 fix
* small fix
2024-11-20 17:18:36 +08:00
Ruonan Wang
54c62feb74
[NPU] dump prefill IR for further C++ solution ( #12402 )
...
* save prefill ir
* fix
* shorten convert time
* fix
* fix
* fix
* fix
* fix style
* dump config.json
* meet review
* small fix
2024-11-20 15:20:05 +08:00
Wang, Jian4
1bfcbc0640
Add multimodal benchmark ( #12415 )
...
* add benchmark multimodal
* update
* update
* update
2024-11-20 14:21:13 +08:00
SONG Ge
ff3f7cb25f
Fix speech_paraformer issue with unexpected changes ( #12416 )
...
* Fix speech_paraformer issue with unexpected changes
* Add paraformer version specified
2024-11-19 15:01:20 +08:00
joan726
a9cb70a71c
Add install_windows_gpu.zh-CN.md and install_linux_gpu.zh-CN.md ( #12409 )
...
* Add install_linux_gpu.zh-CN.md
* Add install_windows_gpu.zh-CN.md
* Update llama_cpp_quickstart.zh-CN.md
Related links updated to zh-CN version.
* Update install_linux_gpu.zh-CN.md
Added link to English version.
* Update install_windows_gpu.zh-CN.md
Add the link to English version.
* Update install_windows_gpu.md
Add the link to CN version.
* Update install_linux_gpu.md
Add the link to CN version.
* Update README.zh-CN.md
Modified the related link to zh-CN version.
2024-11-19 14:39:53 +08:00
Guancheng Fu
d6057f6dd2
Update benchmark_vllm_throughput.py ( #12414 )
2024-11-19 10:41:43 +08:00
Yuwen Hu
a69395f31f
Support performance mode of GLM4 model ( #12401 )
...
* Initial support of prepare generation args for transformers 445
* Small fix to chatglm4 model optimization
* Small fix
* fix glm4 position id
* fix glm4 error
* Small change in conditon & fix based on comments
* Style fixes
---------
Co-authored-by: cyita <yitastudy@gmail.com>
2024-11-18 18:46:52 +08:00
Song Fuchang
d2c821d458
Add missing arguments in pipeline parallel generate method ( #12142 )
...
Add two arguments: negative_prompt_ids and negative_prompt_attention_mask to generate method in pipeline_parallel.py.
2024-11-18 13:50:18 +08:00
Yishuo Wang
3d5fbf2069
update batch kernel condition ( #12408 )
2024-11-15 13:47:05 +08:00
Ruonan Wang
6c5e8fc70c
fix again ( #12407 )
2024-11-15 11:57:58 +08:00
Ruonan Wang
fcc0fa7316
fix workflow again ( #12406 )
...
* fix again
* fix name
2024-11-15 11:01:35 +08:00
Yuwen Hu
d1cde7fac4
Tiny doc fix ( #12405 )
2024-11-15 10:28:38 +08:00
Ruonan Wang
548dec5185
fix npu pipeline workflow ( #12404 )
2024-11-15 10:01:33 +08:00
binbin Deng
d4d949443f
[NPU] change attention_mask to fp16 ( #12400 )
2024-11-14 17:20:29 +08:00
Qiyuan Gong
7e50ff113c
Add padding_token=eos_token for GPU trl QLora example ( #12398 )
...
* Avoid tokenizer doesn't have a padding token error.
2024-11-14 10:51:30 +08:00
SONG Ge
d2cbcb060c
Add initial support for modeling_xlm encoder on NPU ( #12393 )
...
* Add initial support for modeling_xlm encoder on NPU
* Add EmbeddingModel class to keep the same usage with bce and npu fp16 linear convert
* Optimize currently implementation to support EmbeddingModel.encode API and convert other torch modules to NPU
* Add related example and documents
2024-11-14 10:50:27 +08:00
Xu, Shuo
6726b198fd
Update readme & doc for the vllm upgrade to v0.6.2 ( #12399 )
...
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
2024-11-14 10:28:15 +08:00
Yina Chen
59b01fa7d2
small fix ( #12397 )
2024-11-14 10:03:36 +08:00
Yishuo Wang
00fce5c940
use new q4_0 batch kernel ( #12396 )
2024-11-13 18:37:34 +08:00
Yina Chen
d6d63d6b84
[NPU] Qwen prefill attn_mask type hotfix ( #12395 )
...
* qwen prefill attn_mask type fp16
* update
2024-11-13 17:51:34 +08:00
Yina Chen
9220babaab
qwen prefill attn_mask type fp16 ( #12394 )
2024-11-13 17:45:26 +08:00
Yuwen Hu
1158f91648
Fix llava with multi-image inputs ( #12384 )
2024-11-13 09:27:50 +08:00
Shaojun Liu
27152476e1
minor fix ( #12389 )
2024-11-12 22:36:43 +08:00
Xu, Shuo
dd8964ba9c
changed inference-cpp/Dockerfile ( #12386 )
...
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
Co-authored-by: Shaojun Liu <61072813+liu-shaojun@users.noreply.github.com>
2024-11-12 20:40:21 +08:00
Guancheng Fu
0ee54fc55f
Upgrade to vllm 0.6.2 ( #12338 )
...
* Initial updates for vllm 0.6.2
* fix
* Change Dockerfile to support v062
* Fix
* fix examples
* Fix
* done
* fix
* Update engine.py
* Fix Dockerfile to original path
* fix
* add option
* fix
* fix
* fix
* fix
---------
Co-authored-by: xiangyuT <xiangyu.tian@intel.com>
2024-11-12 20:35:34 +08:00
Jun Wang
4376fdee62
Decouple the openwebui and the ollama. in inference-cpp-xpu dockerfile ( #12382 )
...
* remove the openwebui in inference-cpp-xpu dockerfile
* update docker_cpp_xpu_quickstart.md
* add sample output in inference-cpp/readme
* remove the openwebui in main readme
* remove the openwebui in main readme
2024-11-12 20:15:23 +08:00
Ruonan Wang
6bf5a8c230
[NPU] Update qwen2 compile config ( #12383 )
...
* update
* fix
2024-11-12 16:59:44 +08:00
binbin Deng
7a97fbb779
Support vpm and resampler module of minicpm-v on NPU ( #12375 )
2024-11-12 15:59:55 +08:00
Wang, Jian4
85c9279e6e
Update llama-cpp docker usage ( #12387 )
2024-11-12 15:30:17 +08:00
