apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 00:57:33 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
2,962 Commits 23 Branches 7 Tags
ffec66097caa1338c6c8254a1cabc8ccb27e0ef5
Commit Graph

57 Commits

Author SHA1 Message Date
chenjian
ffec66097c [optimize] Optimize prefix caching in v1 release/2.1 (#3823) 
* [optimize] Optimize prefix caching in v1

* [optimize] Optimize prefix caching in v1

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
 2025-09-04 19:25:02 +08:00
chen
1e19833ba5 [CP] CP Lm head fp32 and temp_logprob to release/2.1 (#3766) 
* [Feature] Add temp_scaled_logprobs and top_p_normalized_logprobs parameters for logits and logprobs post processing (#3552)

* [feature] Add temp_scaled_logprobs and top_p_normalized_logprobs parameters for logits and logprobs post processing

* infer engine support temp_scaled_logprobs and top_p_normalized_logprobs

* delete some code

* code check

* code check and add doc

* fix tokenizer.decoder(-1), return 'Invalid Token'

* add ci for temp_scaled and top_p logprobs

* check test

* check seq len time shape

* logprob clip inf

---------

Co-authored-by: sunlei1024 <sunlei5788@gmail.com>

* [Precision] Support lm_head layer running in float32 (#3597)

* support lm_head fp32 bf16 fp16

* support lm_head fp32 bf16 fp16

* add doc and check code

* lm_head_fp32 specify lm_head as fp32

* code check

* check doc

* code check

---------

Co-authored-by: sunlei1024 <sunlei5788@gmail.com>
 2025-09-01 19:56:54 +08:00
Jiang-Jia-Jun
3364af767b Revert "[BugFix] Modify the bug in Qwen2 when enabling ENABLE_V1_KVCACHE_SCHE…" (#3719) 
This reverts commit 578b8c5da2.
 2025-08-29 19:55:50 +08:00
lizexu123
578b8c5da2 [BugFix] Modify the bug in Qwen2 when enabling ENABLE_V1_KVCACHE_SCHEDULER. (#3670) 
* merge 2.1

* fix

* pre-commit

* fix
 2025-08-29 19:53:44 +08:00
ltd0924
8517e04956 [bugfix]PR3663 parameter is 0 (#3679) 
* Update engine.py

* Update engine_client.py

* Update engine.py

* Update engine.py
 2025-08-29 11:46:42 +08:00
李泳桦
aad9d3564e [feat] add metrics for yiyan adapter (#3615) 
* [feat] add metrics for yiyan adapter (#3219)

* [feat] add metrics for yiyan adapter

* [fix] fix metrics num_requests_waiting and num_requests_running

* [fix] fix metrics gpu_cache_usage_perc

* [refactor] change where requests_number increases

* [chore] rename xxx_block_num as xxx_gpu_block_num, and update their values accordingly

* [chore] delete useless code

* [fix] fix error
 2025-08-28 21:16:58 +08:00
Jiang-Jia-Jun
6039cdc2c5 Revert "[BugFix] fix parameter is 0 (#3663)" (#3681) 
This reverts commit 6a90cfd144.
 2025-08-28 15:55:55 +08:00
ltd0924
6a90cfd144 [BugFix] fix parameter is 0 (#3663) 
* Update engine.py

* Update engine_client.py
 2025-08-28 09:52:17 +08:00
李泳桦
df27a488b1 [fix] fix ZmqIpcClient.close() error (#3600) 2025-08-26 10:16:41 +08:00
Zero Rains
f8d3255520 [Cherry-Pick] Launch expert_service before kv_cache initialization in worker_process (#3558) 
* launch expert_service before kv_cache initialization

* update code

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
 2025-08-23 13:08:34 +08:00
chenjian
e8af92aab7 [Feature] Support mixed deployment with yiyan adapter (#3533) 
* [Feature] Support mixed deployment with yiyan adapter

* [Feature] Support mixed deployment with yiyan adapter

* fix merge

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
 2025-08-23 09:56:47 +08:00
ltd0924
c18975366e [BUGFIX] fix ep mixed bug (#3513) 
* Update expert_service.py

* Update engine.py

* Update engine.py

* Update engine.py

* Update expert_service.py

* Update engine.py
 2025-08-22 11:35:50 +08:00
luukunn
4a9c04a746 [Feature] add tool parser (#3518) 
* [Feature] Pass through the `chat_template_kwargs` to the data processing module (#3421)

* fix chat_template_args

* fix args

* add offline

* add offline

* fix

* fix

* fix default enable_thinking value

* fix default enable_thinking value

* modify condition

* Revert "modify condition"

This reverts commit 26430bdeb1.

* fix unit test

* add Tool Parser (#3272)

* add tool-parser

* add tool-parser

* add tool parser

* add tool parser

* fix

* add offline

* add offline

* fix

* parsers:tool&reasoning

* 修改tool parser名称·

* update

* fix reasoning-parser

* add requirements

* fix finish reason

* fix

* fix reasoning-parser

* fix

* fix

* fix

* fix

* fix

---------

Co-authored-by: zhuzixuan <zhuzixuan@baidu.com>

* [Feature] add tool parser (#3483)

* add tool parser

* add x1 enable_thinking

* restart ci

* fix vl reasoning parser

* modify call style

* modify call style

* add offline enablethinking

* fix completion

* fix

* fix unit test

* fix unit test

* fix unit test

* fix vl reasoning parser

* fix vl reasoning parser

* fix unit test

---------

Co-authored-by: zhuzixuan <zhuzixuan@baidu.com>
 2025-08-22 11:14:35 +08:00
luukunn
d07338f932 [Feature] Pass through the chat_template_kwargs to the data processing module (#3421) (#3469) 
* fix chat_template_args

* fix args

* add offline

* add offline

* fix

* fix

* fix default enable_thinking value

* fix default enable_thinking value

* modify condition

* Revert "modify condition"

This reverts commit 26430bdeb1.

* fix unit test
 2025-08-19 17:40:12 +08:00
Jiang-Jia-Jun
28918702c2 Revert "Merge branch 'feature/online/vs_think_20250813' into release/2.1" 
This reverts commit 02596fc537, reversing
changes made to 03347626a6.
 2025-08-14 17:20:29 +08:00
Jiang-Jia-Jun
02596fc537 Merge branch 'feature/online/vs_think_20250813' into release/2.1 2025-08-14 17:13:36 +08:00
JYChen
4870919682 fix stopseq error info (#3342) 
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
 2025-08-14 10:45:05 +08:00
luukunn
81092c0fe3 add tool parser 2025-08-13 16:06:22 +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
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
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
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
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
ltd0924
f935d6f862 [BugFix] fix multinode deployment (#2977) 2025-07-24 15:04:04 +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
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
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
Zero Rains
25698d56d1 polish code with new pre-commit rule (#2923) 2025-07-19 23:19:27 +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
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
Zero Rains
e7bcbbab52 Merge vl execution path into normal execution path (#2829) 
* merge vl model into gpu_model runner

Change-Id: I9f4691a3d5f135e8d72b1d58abcd15ef3aa3f2a6

* fix chinese

Change-Id: Ic7405109b984c21e076fb3b01ff6feb571d0119a

* fix the parse parameter

Change-Id: I4cd62ee87c06220af580d91e347145d4394917fe

* fix the bug in online_inference

Change-Id: Idb111bb2114e83017c4050b2a68cf039c6d3c559

* polish code

Change-Id: I7d4194102c2f1b0743b74fbd5fc284eb8ef4d17c
 2025-07-15 22:20:03 +08:00
lddfym
b5e4288704 Global scheduler supports configuring hot updates (#2807) 
* Check if the controller port is available

* Global scheduler supports configuring hot updates

* add interface: /controller/scheduler

* add interface: /controller/scheduler
 2025-07-11 13:38:07 +08:00
chen
d33105baeb [Feature] Online Chat API Support Return logprobs (#2777) 
* online chat support logprobs

* check xpu

* check vl_gpu_model_runner and xpu_model_runner

* get_worker() check platform
 2025-07-10 16:33:40 +08:00
0x3878f
1d8af7ab73 Add env variable for dy2st (#2779) 2025-07-10 11:06:06 +08:00