ming1753
d6bf6de5e6
[Bug Fix] Fix mm performance degradation ( #3942 )
...
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
* [Bug Fix] Fix mm performance degradation
* formate
---------
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com >
Co-authored-by: chenjian <1435317881@qq.com >
2025-09-08 00:32:22 +08:00
chenjian
38e734e183
[Feature] support hierarchical cache in v1 ( #3939 )
2025-09-08 00:31:34 +08:00
bukejiyu
051e4a881c
ignore ( #3949 )
2025-09-07 23:57:48 +08:00
chenjian
b2bb37d7c0
[Fix] when prompt token ids is numpy ( #3944 )
2025-09-07 23:02:03 +08:00
CSWYF3634076
c6e2a37a95
[BugFix] qwen2.5vl enable_thinking=true bug fix ( #3920 )
2025-09-07 21:06:36 +08:00
chenjian
8d77c1cb51
[Optimize] optimize prefix cache in release22 ( #3889 )
...
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
* optimize prefix cache in release22
* optimize prefix cache in release22
* fix worker
* fix
* fix
---------
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com >
2025-09-06 09:52:01 +08:00
chenjian
41cd3e24c9
[Feature] Enable prefix caching as default ( #3816 )
...
* [Feature] Enable prefix caching as default
* [Feature] Enable prefix caching as default
* Set prefix caching as default
* skip dynamic load
* fix kill bug
* fix kill bug
* fix kill bug
* fix ci
* fix
---------
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com >
2025-09-06 09:51:34 +08:00
Zhang Yulong
11b18e5ef0
add cache queue port ( #3904 ) ( #3926 )
...
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
* add cache queue port
* add cache queue port
* add cache queue port
2025-09-06 00:00:12 +08:00
freeliuzc
e2c764fd5a
update hybrid-mtp-with-ngram ( #3924 )
2025-09-05 23:06:57 +08:00
lizhenyun01
2d975e16b0
[BugFix] fix TaskQueue dp_id in multi node ( #3919 )
2025-09-05 22:29:26 +08:00
chenjian
8915c8411d
Revert "[Feature] Setting number of apiserver workers automatically ( #3794 )" ( #3918 )
...
This reverts commit d1d063e4af
2025-09-05 21:06:50 +08:00
yinwei
77c1bd0813
[XPU]Fixed the issue of performance degradation caused by enabling ENABLE_V1_KVCACHE_SCHEDULER ( #3900 )
...
* fix bug
* fix bug
* update
* udpate
* update
2025-09-05 19:17:25 +08:00
Yuanle Liu
473cde779f
paddleformers==0.2.1 ( #3925 )
2025-09-05 19:06:15 +08:00
chen
335d1c8e8f
【CP】Compatible with EB 0.3B torch model arch ( #3914 )
...
* fix
* check
2025-09-05 19:05:07 +08:00
ltd0924
173e4df982
[Fix] mv connection_manager init ( #3902 )
...
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
* Update serving_chat.py
* Update serving_completion.py
* Update serving_completion.py
* mv connection_manager init
---------
Co-authored-by: Yuanle Liu <yuanlehome@163.com >
2025-09-05 17:42:36 +08:00
lizhenyun01
199f88ce1e
support tpep weight load ( #3882 )
2025-09-05 13:56:29 +08:00
ltd0924
55ebe855c0
[Feature] support controller port in multi api server ( #3895 )
...
* fix scheduler bug
* fix
* Update api_server.py
* Update multi_api_server.py
2025-09-05 13:38:58 +08:00
zhouchong
deb7ad205f
fix qwen_vl_processor miss image_patch_id ( #3894 )
...
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com >
2025-09-05 11:32:34 +08:00
Yuanle Liu
e9f72df918
paddleformers==0.1.4 ( #3908 )
2025-09-05 11:25:57 +08:00
chenjian
8567ada09e
[Fix] disable scheduler v1 in guided decoding ( #3877 )
...
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
* disable scheduler v1 in guided decoding
* disable scheduler v1 in guided decoding
2025-09-04 20:54:55 +08:00
YuBaoku
afcde19277
[CI] update paddleformers==0.2 in release/2.2 ( #3828 )
...
* [DEBUG] Adapt validation for paddleformers==0.2 in release/2.2
* [CI] update paddleformers==0.2 in release/2.2
2025-09-04 20:12:37 +08:00
lizhenyun01
d40d3a5a4f
fix DP&&TP ( #3872 )
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
2025-09-04 14:38:26 +08:00
luukunn
b8d0f1c081
[bug] fix finish reason ( #3858 )
...
* add reasoning parser plugin
* fix finish reason
---------
Co-authored-by: Yuanle Liu <yuanlehome@163.com >
2025-09-04 14:36:03 +08:00
ltd0924
8550e19008
[bugfix] scheduler ( #3871 )
...
* fix scheduler bug
* fix
* Update api_server.py
2025-09-04 11:34:12 +08:00
chenjian
a0c03510c0
[Bug fix] Fix prompt token ids dtype in v1 ( #3861 )
2025-09-04 11:02:37 +08:00
chenjian
fb1e0d6a87
[Feature] Set scheduler v1 as default ( #3812 )
...
* [Feature] Set scheduler v1 as default
* [Feature] Set scheduler v1 as default
* [Feature] Set scheduler v1 as default
* [Feature] Set scheduler v1 as default
* [Feature] Set scheduler v1 as default
* [Feature] Set scheduler v1 as default
2025-09-04 11:02:10 +08:00
gaoziyuan
fbf0e9d2aa
fix mem boom in ep ( #3852 )
2025-09-04 10:38:34 +08:00
SunLei
8c0e7d6fe9
Support for async processor added. ( #3870 )
...
* Support for async processor added.
* remove yappi code
2025-09-04 10:35:08 +08:00
yangjianfengo1
b56b015d85
fix port ( #3865 )
...
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com >
2025-09-04 10:02:08 +08:00
ming1753
1432e336d7
[Bug Fix] Fix bug of multimodal inputs only text ( #3850 )
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
2025-09-03 19:48:10 +08:00
yangjianfengo1
9213a58a06
【Fix bug] w4afp8 的nblock固定为256，并且fa3的append attn 增加mask参数 ( #3771 ) ( #3835 )
...
* fix w4afp8
* 增加集中式配置
* codestyle
* fix fa3 append attn
2025-09-03 19:36:45 +08:00
plusNew001
87ef0f5d30
[XPU] Update XPU stable xvllm and xtdk version for 2.2 & Change CI Case ( #3855 )
...
* Update no_proxy environment variable in CI workflow
* Install lsof and kill api_server processes
Install lsof tool and kill processes using it.
* Update dependency versions for stable release
* Update CI script to use stable dependencies
2025-09-03 19:33:06 +08:00
plusNew001
abcd2148c0
[XPU]Update XPU CI Case ( #3844 )
...
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
* Update no_proxy environment variable in CI workflow
* Install lsof and kill api_server processes
Install lsof tool and kill processes using it.
2025-09-03 15:29:47 +08:00
gaoziyuan
05b6591c23
【BugFix】add moe noaux_tc tatics in trition backend ( #3821 )
...
* add moe noaux_tc tatics in trition backend
* fix
* add dp config
2025-09-03 13:28:44 +08:00
plusNew001
42402c80e9
Update installation method for paddlepaddle-xpu ( #3834 )
2025-09-03 11:28:27 +08:00
luukunn
1968c65849
add reasoning parser plugin ( #3820 )
2025-09-03 11:17:13 +08:00
ltd0924
37cb37b7f2
[BugFix] fix scheduler ( #3818 )
...
* fix scheduler bug
* fix
2025-09-03 11:16:49 +08:00
bukejiyu
f975f7de2f
[v1loader]Reduce EB300B model loading time ( #3700 ) ( #3810 )
...
* speed up eb45
* update
2025-09-03 10:14:31 +08:00
Yuanle Liu
174510180a
[BugFix] fix error of import paddle.base.core.Config ( #3761 ) ( #3804 )
...
* 延迟 import Config
* support chunked_prefill
* support chunked_prefill
2025-09-03 10:14:03 +08:00
ltd0924
5cda326ba2
Update qwen_vl_processor.py ( #3806 )
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
2025-09-02 21:56:24 +08:00
RAM
a6c8f17431
[Executor] Fix bug of import paddle with RLHF ( #3781 ) ( #3817 )
2025-09-02 21:42:59 +08:00
ltd0924
cd09384a14
[BugFix] fix max streaming tokens invalid ( #3799 )
...
* Update serving_chat.py
* Update serving_completion.py
* Update serving_completion.py
2025-09-02 21:03:13 +08:00
ltd0924
0f42771a84
[Feature] support model weight update in ep ( #3802 )
...
* Update config.py
* Update ep.py
* Update fused_moe_backend_base.py
* Update dynamic_weight_manager.py
* Update worker_process.py
* fix ci
2025-09-02 20:52:47 +08:00
Jiang-Jia-Jun
d1d063e4af
[Feature] Setting number of apiserver workers automatically ( #3794 )
...
Co-authored-by: Jiang-Jia-Jun <jiangjiajun@baidu.com >
2025-09-02 17:19:07 +08:00
kevin
a86b35ab49
Fix chunked prefill ( #3778 )
...
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
* update enable chunked_prefill
* update code
* update code
* update code
2025-09-02 13:41:55 +08:00
YUNSHEN XIE
0cdbc950b5
fix ce compile task upload error ( #3788 )
2025-09-02 11:52:50 +08:00
YUNSHEN XIE
2b0a745d57
fix ce build job ( #3777 )
2025-09-02 10:53:26 +08:00
Jiang-Jia-Jun
1953c7c759
Update FASTDEPLOY_VERSION to 2.2.0
2025-08-31 21:31:12 +08:00
chenjian
465065cd19
[Bug fix] Fix prefix cache in V1 ( #3715 )
...
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Deploy GitHub Pages / deploy (push) Has been cancelled
Publish Job / publish_pre_check (push) Has been cancelled
Publish Job / print_publish_pre_check_outputs (push) Has been cancelled
Publish Job / FD-Clone-Linux (push) Has been cancelled
Publish Job / Show Code Archive Output (push) Has been cancelled
Publish Job / BUILD_SM8090 (push) Has been cancelled
Publish Job / BUILD_SM8689 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8090 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8689 (push) Has been cancelled
Publish Job / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
Publish Job / Run FastDeploy LogProb Tests (push) Has been cancelled
Publish Job / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
Publish Job / Run Base Tests (push) Has been cancelled
Publish Job / Run Accuracy Tests (push) Has been cancelled
* [Bug fix] Fix prefix cache in V1
* fix code style
2025-08-31 21:29:33 +08:00
lizhenyun01
bed09ae8f8
fix mask_offset in append_attn ( #3745 )
...
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Deploy GitHub Pages / deploy (push) Has been cancelled
* fix mask_offset in append_attn
* fix test
2025-08-31 15:03:16 +08:00
