apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-14 04:44:00 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity
2,908 Commits 16 Branches 8 Tags
edf1ca07afb47f37e2042489ce02249413bbe78a
Commit Graph

68 Commits

Author SHA1 Message Date
luukunn
bbd50c6717 add tool parser 2025-08-14 21:08:49 +08:00
luukunn
132a8ef425 Release/2.1 (#3414) 
* Pre ce modified (#3335) (#3360)

* Pre ce modified (#3335)

* update

* update

* fix

* fix

* update

* update

* update

* fix

* update

* update

* update

* add ut fix pr(3367)

* [Bug Fix] Fix V1 video bug (#3387)

* fix stopseq error info (#3342)

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>

* [BugFix] Fix default log level of paddleformers (#3377)

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>

* [Polish Code] Remove useless notes

* feat(log):add_request_and_response_log (#3392)

* Optimize CI execution workflow. (#3371) (#3384)

* fix

* [BugFix] fix control signal release failed (#3374)

* [BugFix]

* [BugFix]

* [BugFix]

* [BugFix]

* fix

* fix

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>

* Revert "Merge branch 'feature/online/vs_think_20250813' into release/2.1"

This reverts commit 02596fc537, reversing
changes made to 03347626a6.

* [XPU] Fixed the issue of performance degradation caused by enabling ENABLE_V1_KVCACHE_SCHEDULER (#3393)

* fix v1 schedule oom bug

* fix v1 schedule oom bug

* [BugFix] fix ErnieProcessor not set raw_prediction (#3401)

* [Doc]Release fastdeploy-xpu 2.1.0 (#3407)

* fix v1 schedule oom bug

* fix v1 schedule oom bug

* update release note

* [Doc]Release fastdeploy-xpu 2.0.3  (#3408)

* fix v1 schedule oom bug

* fix v1 schedule oom bug

* update release note

* update info

---------

Co-authored-by: YUNSHEN XIE <1084314248@qq.com>
Co-authored-by: ming1753 <61511741+ming1753@users.noreply.github.com>
Co-authored-by: JYChen <zoooo0820@qq.com>
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
Co-authored-by: Jiang-Jia-Jun <jiangjiajun@baidu.com>
Co-authored-by: xiaolei373 <zley373@gmail.com>
Co-authored-by: ltd0924 <32387785+ltd0924@users.noreply.github.com>
Co-authored-by: yinwei <yinwei_hust@163.com>
Co-authored-by: memoryCoderC <1137889088@qq.com>
 2025-08-14 20:53:47 +08:00
Jiang-Jia-Jun
e11331927f [Sync Code] Update vs branch (#3403) 
* Pre ce modified (#3335) (#3360)

* Pre ce modified (#3335)

* update

* update

* fix

* fix

* update

* update

* update

* fix

* update

* update

* update

* add ut fix pr(3367)

* [Bug Fix] Fix V1 video bug (#3387)

* fix stopseq error info (#3342)

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>

* [BugFix] Fix default log level of paddleformers (#3377)

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>

* [Polish Code] Remove useless notes

* feat(log):add_request_and_response_log (#3392)

* Optimize CI execution workflow. (#3371) (#3384)

* fix

* [BugFix] fix control signal release failed (#3374)

* [BugFix]

* [BugFix]

* [BugFix]

* [BugFix]

* fix

* fix

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>

---------

Co-authored-by: YUNSHEN XIE <1084314248@qq.com>
Co-authored-by: ming1753 <61511741+ming1753@users.noreply.github.com>
Co-authored-by: JYChen <zoooo0820@qq.com>
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
Co-authored-by: Jiang-Jia-Jun <jiangjiajun@baidu.com>
Co-authored-by: xiaolei373 <zley373@gmail.com>
Co-authored-by: ltd0924 <32387785+ltd0924@users.noreply.github.com>
 2025-08-14 17:14:45 +08:00
luukunn
81092c0fe3 add tool parser 2025-08-13 16:06:22 +08:00
chenjian
25f51b0611 Fix block num in schduelr v1 for release 2.1 (#3315) 
* fix bug for scheduler v0

* fix block num setting in scheduler v1 for release 2.1

* fix block num setting in scheduler v1 for release 2.1

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
Co-authored-by: YUNSHEN XIE <1084314248@qq.com>
 2025-08-12 00:41:05 +08:00
ming1753
9b07f85f6d [Bug Fix] fix vl V1 schedule bug (#3284) 
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
Co-authored-by: YUNSHEN XIE <1084314248@qq.com>
 2025-08-12 00:40:45 +08:00
chenjian
c000cff744 fix scheduler bug in release2.1 (#3295) 2025-08-10 13:55:22 +08:00
JYChen
1b6f482c15 [Cherry-pick] fix stop seq (#3263) 
* fix out-bound value for stop sequence

* catch error if there are out-of-bounds value

* check in offline mode
 2025-08-07 19:11:37 +08:00
Sunny-bot1
f672a34f95 [FIX 2.1]fix bad_words when sending requests consecutively (#3199) 
* fix bad_words

* fix log

* fix log
 2025-08-06 15:47:27 +08:00
chen
c8dd5976ae fix request_output sampling_params (#3154) 2025-08-01 22:34:33 +08:00
SunLei
dade19d7a4 [Feature] General support for logprobs (#2974) 
* [Feature] support logprobs in chat/completions and completions endpoints

* Temporarily comment out text_offset due to incorrect logic

* Clean up temporary debug prints

* [Feature] support logprobs in offline mode via SamplingParams

* fix: serialize Logprob as dict before zmq send to fix msgpack error

* refactor: remove redundant methods to simplify codebase

* Fix missing fields in CompletionOutput.to_dict affecting msgpack serialization

* refactor: centralize param validation in engine_client to reduce duplication

* revert: rollback changes in offline_demo.py

* revert: rollback changes in offline_demo.py

* [bugfix] fix parameter validation for logprobs

* [bugfix] fix parameter validation for logprobs

* [bugfix] fix parameter validation for logprobs

* [bugfix] fix parameter validation for logprobs

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
 2025-07-31 20:25:56 +08:00
kevin
22cab724e8 [Feature] block scheduler v1 support prefix caching (#3061) 
* block scheduler v1 support prefix cache

* update code

* update code

* fix code bug

* add timeout time

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
 2025-07-31 19:29:19 +08:00
chenjian
32307283f1 Fix bug for offline inference in scheduler v1 (#3117) 2025-07-31 17:54:24 +08:00
chenjian
fe0e3f508b [BUG FIX] Fix bug when preempted request rescheduled (#3080) 
* Fix bug when preempted request rescheduled

* Fix bug when preempted request rescheduled

* Fix bug when preempted request rescheduled
 2025-07-30 22:25:47 +08:00
YuanRisheng
7dfdd157ac [BugFix]Fix ep size (#3092) 
* fix ep

* fix num_layer
 2025-07-30 21:03:12 +08:00
ltd0924
d17886de19 [Feature] support ep in mixed mode (#3001) 
* [LLM] support ep

* Update worker_process.py

* Update expert_service.py

* Update worker_process.py

* format files
 2025-07-30 20:43:39 +08:00
bukejiyu
db698bda01 qwen loader (#3057) 2025-07-30 19:09:38 +08:00
ming1753
5acde4eb43 [Feature] Multimodal Scheduler V1 (#3019) 
* [Feature] Support multimodal scheduler v1

* remove debug log

* fix bug

* fix format

* modify code

* fix bug

* fix bug

* fix bug

* modify code
 2025-07-30 16:05:55 +08:00
YuanRisheng
99a70fc722 unify parallel config (#3070) 2025-07-30 11:41:23 +08:00
Sunny-bot1
74aa31d15b [Feature] support bad_words (#3055) 
* support bad_words

* support online infer bad_words

* update

* add CI test

* update

* update

* update

---------

Co-authored-by: Yuanle Liu <yuanlehome@163.com>
 2025-07-30 09:31:29 +08:00
Zero Rains
b2f9a42d87 [Feature] Support repetition early stop (#3024) 
* support repetition early stop and support user to set the parameter

* remove log

* fix codestyle

* add the early_stop_config to rollout_config

* update config and EarlyStopper class

* fix the bug for triton

* modify the stop method

* update description

* modify the usage for stop_flags

---------

Co-authored-by: Yuanle Liu <yuanlehome@163.com>
 2025-07-29 22:42:54 +08:00
YuanRisheng
502ee92a0a Unify server-side and model-side Config (Part3) (#3047) 
* merge model config

* fix arch

* fix rl
 2025-07-29 17:07:44 +08:00
JYChen
dafe02a7b9 [stop sequence] support stop sequence (#3025) 
* stop seqs in multi-ends

* unittest for gpu stop op

* kernel tid==0
 2025-07-29 14:17:37 +08:00
YuanRisheng
1a815b7a2a Fix Speculative Config bug (#3049) 
* fix speculative bug

* fix rl
 2025-07-29 10:50:48 +08:00
Yuan Xiaolan
b1d787a272 [fix] w4a8 model loading and hadamard config (#3013) 2025-07-28 18:17:59 +08:00
YuanRisheng
bddf403576 Unify server-side and model-side Config (Part2) (#3035) 
* merge speculative and graph opt conifg

* add attr
 2025-07-28 15:31:48 +08:00
YuanRisheng
6ccc10ad47 Unify server-side and model-side Config (Part1) (#3018) 
* move cache config

* fix mtp
 2025-07-28 10:51:52 +08:00
李泳桦
69996a40da [feat] add disable_chat_template in chat api as a substitute for previous raw_request (#3020) 
* [feat] add disable_chat_template in chat api as a substitute for previous raw_request

* [fix] pre-commit code check
 2025-07-25 20:57:32 +08:00
Zero Rains
0fb37ab7e4 update flake8 version to support pre-commit in python3.12 (#3000) 
* update flake8 version to support pre-commit in python3.12

* polish code
 2025-07-24 01:43:31 -07:00
ltd0924
f935d6f862 [BugFix] fix multinode deployment (#2977) 2025-07-24 15:04:04 +08:00
Yzc216
e14587a954 [Feature] multi-source download (#2986) 
* multi-source download

* multi-source download

* huggingface download revision

* requirement

* style

* add revision arg

* test

* pre-commit
 2025-07-24 14:26:37 +08:00
chenjian
85a78d695d [Feature] Support block scheduler v1 for FD (#2928) 
* Support FD block scheduler v1

* Support FD block scheduler v1

* Support FD block scheduler v1

* Fix according to copilot review

* Fix according to review

* Remove is_dummy

* Fix bug when real_bsz=1

* Fix infer first token cost time

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
 2025-07-23 20:31:31 +08:00
Ryan
95b5af24db [SOT] Add sot warmup (NVIDIA GPU Only) (#2929)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details 
* add sot warmup

* fix code style

* change batch_size list

* add param to config

* rm free_list settings && set sot_warmup_sizes

* finish debug with dynamic dims by type annotations

* add profile_run guard

* rm sth useless
 2025-07-22 21:36:14 +08:00
Zero Rains
89a485b69f [Feature] Support using prefix-caching + cudagraph for inference (#2924) 
* fix the bug in cudagraph+prefix-caching but still have some bug with profile

Change-Id: Ibf2ba3f2e3b08641d03f4b1391d7c862c3efa397

* add the signal to make sure cache manager launched

* fix judge condition

* reomove useless control

* update control stream

* update

* fix xpu

* change the do_profile flag

* update

* add new threads to init cache_manager

---------

Co-authored-by: RAM <gstian5555@outlook.com>
 2025-07-22 00:59:45 -07:00
Nyakku Shigure
48e6a0ca26 [SOT] Mark dynamic dims by type annotations (#2771)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details 
* [SOT] Mark dynamic dims by type annotations

* fix conflict of forward_meta

* mark more attn backend

* fix missing annotated and add env SOT_SPECIALIZED_DIM_NUMBERS

* auto infer implicit 0 dim dynamic dim

* revert manual marked dims

* revert missing update

* auto infer can use unsafe code in warmup stage

* check -> type_match

* fix codestyle

* restore blank line

* empty commit

* add need_warmup nonlocal;

* add doc for resolver

* add missing type hints

* unquote "ForwardMeta"
 2025-07-22 00:23:52 -07:00
zhink
0262ef7eb3 custom all reduce support cuda graph (#2938)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details 
* Support enabling cuda graph and custom all reduce at the same time, and fix the overwritten custom all reduce flag

* rename communication_op to communication
 2025-07-21 22:52:03 +08:00
李泳桦
8a619e9db5 [Feature] Add return_token_ids, prompt_token_ids, and delete training, raw_request in request body (#2940) 
* [feat] add return_token_ids, prompt_token_ids, delete raw_request in request body

* [fix] return_token_ids not working in curl request

* [test] improve some test cases of return_token_ids and prompt_token_ids

* [fix] the server responds ok even if request.messages is an empty list
 2025-07-21 19:31:14 +08:00
Yuanle Liu
2f74e93d7e use dist.all_reduce(min) to sync num_blocks_local (#2933) 
* pre-commit all files check

* reduce min num_blocks_local

* fix nranks=1

* pre-commit when commit-msg
 2025-07-21 01:23:36 -07:00
lizexu123
67990e0572 [Feature] support min_p_sampling (#2872)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details 
* Fastdeploy support min_p

* add test_min_p

* fix

* min_p_sampling

* update

* delete vl_gpu_model_runner.py

* fix

* Align usage of min_p with vLLM

* fix

* modified unit test

* fix test_min_sampling

* pre-commit all files

* fix

* fix

* fix

* fix xpu_model_runner.py
 2025-07-20 23:17:59 -07:00
Zero Rains
25698d56d1 polish code with new pre-commit rule (#2923) 2025-07-19 23:19:27 +08:00
ltd0924
4b14dca1d6 [LLM] delete fixed slots (#2893)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details
2025-07-17 19:19:54 +08:00
ltd0924
b630031414 [LLM] fix serval bugs (#2878) 2025-07-17 14:21:05 +08:00
Yuanle Liu
dbb9e2506b Fix rollout_model init (#2881) 2025-07-16 22:36:21 -07:00
sg263
52aca233e8 [Trace] fix annotation when add opentelemetry (#2869) 
* add opentelemetry

* add opentelemetry

* add opentelemetry on dequeue

* add opentelemetry on dequeue

* add opentelemetry on dequeue

* fix annotation

* fix annotation when add opentelemetry

* fix opentelemetry-instrumentation-fastapi

* fix pentelemetry-bootstrap

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
 2025-07-17 10:29:16 +08:00
ltd0924
9c25dcca0b [LLM] Update Multinode Deployment (#2830)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details 
* [LLM] fix multinode bugs

* [LLM] update multinode deployment

* [LLM] update multinode deployment

* [LLM] update multinode deployment

* [LLM] update multinode deployment

* [LLM] update multinode deployment

* [LLM] fix ci bugs

* Update fastdeploy/engine/args_utils.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* [LLM] update random port

* [LLM] update random port

* [LLM] fix ci bugs

* fix ci bugs

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
 2025-07-16 23:42:54 +08:00
ltd0924
d245d1ca6c [LLM] support send batch data and aggregate data (#2860) 
* [LLM] support send batch data and aggregate data

* [LLM] fix ci bugs

* [LLM] fix ci bugs

* [LLM] fix ci bugs

* [LLM] fix ci bugs

* [LLM] update
 2025-07-16 23:42:20 +08:00
sg263
42b80182e0 [Trace] add opentelemetry (#2852) 
* add opentelemetry

* add opentelemetry

* add opentelemetry on dequeue

* add opentelemetry on dequeue

* add opentelemetry on dequeue

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
 2025-07-16 15:33:25 +08:00
Yuanle Liu
dda4a9f848 rl update (#2861) 2025-07-16 00:33:10 -07:00
yangjianfengo1
a83a3eea5f 将FLAGS_max_partition_size修改为环境变量获取 (#2854) 2025-07-16 14:14:21 +08:00
RAM
0fad10b35a [Executor] CUDA Graph support padding batch (#2844) 
* cuda graph support padding batch

* Integrate the startup parameters for the graph optimization backend and provide support for user - defined capture sizes.

* Do not insert max_num_seqs when the user specifies a capture list

* Support set graph optimization config from YAML file

* update cuda graph ci

* fix ci bug

* fix ci bug
 2025-07-15 19:49:01 -07:00