apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 21 Packages Projects Releases Wiki Activity
4,670 Commits 41 Branches 17 Tags
049c807d86b29748ed3de70151fcd7d7254176d1
Commit Graph

4670 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
mouxin 049c807d86 [Docs] Update the document (#6539) 
Co-authored-by: mouxin <mouxin@baidu.com>
 2026-02-27 19:21:10 +08:00
cmcamdy 13447279aa [XPU] Fix PD + MTP (#6495) 
* fix pd + mtp

* fix code style

* fix PD + MTP, D get P's first token

* add anno for gpu(speculate_update)

* update draft insertv1

* fix wapper & kernel

* fix wapper

* fix code stype
 2026-02-27 19:07:35 +08:00
xunyoyo 12f754ef38 [CI] 【Hackathon 10th Spring No.42】功能模块 fastdeploy/entrypoints/openai/serving_chat.py单测补充 (#6112) 
* test: expand OpenAI serving chat coverage

* Import RequestOutput in test_serving_chat.py

* Reorder import statements in test_serving_chat.py

* test: fix tool_calls finish_reason case

* test: refine serving_chat coverage

* test: format serving_chat tests

---------

Co-authored-by: CSWYF3634076 <wangyafeng@baidu.com>
 2026-02-27 16:32:46 +08:00
ZeLong Li 81ea3674b0 [CI] 【Hackathon 10th Spring No.26】功能模块 fastdeploy/utils.py 单测补充 (#6146) 
test (#6146)
Co-authored-by: CSWYF3634076 <wangyafeng@baidu.com>
 2026-02-27 16:28:40 +08:00
xunyoyo ff61a7f5a1 [CI] 【Hackathon 10th Spring No.40】功能模块 fastdeploy/model_executor/layers/linear.py单测补充 (#6107) 
* Add linear layer tests for model executor

* Refine linear layer tests for uncovered branches

* Refactor and enhance tests for linear layers

Refactor test_linear.py by removing unused imports and redundant code, and updating model configuration parameters. Add new tests for linear layers and their loading mechanisms.

* test: patch row-parallel alltoall in unit test

* test: avoid alltoall reshape failure in row-parallel

* test: expand linear coverage targets

* Refine linear tests per review feedback

* Fix linear tests for pre-sharded config and qkv fixture

---------

Co-authored-by: CSWYF3634076 <wangyafeng@baidu.com>
 2026-02-27 16:25:23 +08:00
JYChen c6d8fbe526 [BugFix] fix log with paddlefleet.ops (#6528) 2026-02-27 14:34:29 +08:00
周周周 1503443871 add dsv3 mixed deploy as EP16 TP8 (#6525) 2026-02-27 14:08:25 +08:00
luukunn 16de778343 update FD_USAGE_STATS_SERVER (#6524) 2026-02-27 13:28:57 +08:00
sunxin 53aaac69da [Optimization] Enable BF16 gate computation for GLM and Qwen (#6457) 
* gate bf16

* add gate-fp32

* fix

* update baseline

* update

* update

* fix
 2026-02-26 21:08:46 -08:00
gongweibao edd31e8849 [Feature] Add Deterministic Inference Support (#6476) 
* add

* [tests] Add Paddle attention determinism tests and refactor resource manager

Add comprehensive determinism tests for Paddle attention layer and refactor
resource manager for deterministic mode support.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* add

* add

* add

* add

* add more

* add more

* fixsome

* fixsome

* fix bugs

* fix bugs

* only in gpu

* add docs

* fix comments

* fix some

* fix some

* fix comments

* add more

* fix potential problem

* remove not need

* remove not need

* remove no need

* fix bug

* fix bugs

* fix comments

* fix comments

* Update tests/ce/deterministic/test_determinism_verification.py

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

* Update tests/inter_communicator/test_ipc_signal.py

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

* Update tests/layers/test_paddle_attention_determinism.py

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

* Update tests/engine/test_sampling_params_determinism.py

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

* Update tests/layers/test_paddle_attention_determinism.py

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

* Update tests/layers/test_paddle_attention_determinism_standalone.py

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

* fix comments

* fix import error

* fix a bug

* fix bugs

* fix bugs

* fix coverage

* refine codes

* refine code

* fix comments

* fix comments

* fix comments

* rm not need

* fix allreduce large tensor bug

* mv log files

* mv log files

* add files

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
 2026-02-26 19:31:51 -08:00
zccjjj c34cb2a8c2 [XPU] [bugfix] fix moe_ffn_quant_type_map bugs about datatype and tensorshape (#6337) 2026-02-27 09:55:41 +08:00
jc 7b1d787b4b [BugFix] Fix storage_backend_type comparison bug in cache_transfer_manager.py (#6514) 
Co-authored-by: root <root@tjzj-inf-sci-k8s-hzz1-h62ni7-2178.tjzj.baidu.com>
 2026-02-26 19:32:24 +08:00
MingkunZhang c369f7139f [Metax][Fix] fix error based pr #6493 (#6521) 2026-02-26 18:41:35 +08:00
chen 2d1531f3cb dev opensource model support fa4/flashmasV2/V3 (#6518) 2026-02-26 17:46:05 +08:00
kesmeey bf14ea18aa tests: fix cache_transfer_manager threading and init mocks (#6502) 
tests: fix cache_transfer_manager threading and init mocks
 2026-02-26 17:32:51 +08:00
Zhang Yulong ff20a3cc02 [benchmark] update tool call (#6519) 2026-02-26 17:06:54 +08:00
yinwei 256651e9de Add PD Cudagraph CI Case 2026-02-26 17:01:20 +08:00
gongweibao 2541462f7e [Feature][Docs] Add Python-only quick install mode (BUILD_WHEEL=2) to build.sh (#6503) 
* add pythononly func

* add

* add more feature

* add safe check

* add rsync check

* add

* add

* refine docs

* add installation

* add installation
 2026-02-26 16:17:41 +08:00
AIbin 47bfd45bb6 [Docs]add deepseek model doc (#6513) 
* add deepseek model doc
 2026-02-26 14:08:19 +08:00
MingkunZhang b56a4099c0 [Metax][Docs] update metax guidance documents (#6515) 2026-02-26 14:04:23 +08:00
GoldPancake 2178f2829b [Speculative Decoding] Support suffix decoding (#6403) 
* support suffix decoding
 2026-02-26 11:42:05 +08:00
Yuanle Liu 6d3fede240 [OP][Feature] 统一 limit_thinking_content_length CUDA 算子，支持回复长度限制与注入序列 (#6493) 
* Initial plan

* Migrate PRs #6311, #6129, #6305 to develop and merge unit tests

Co-authored-by: yuanlehome <23653004+yuanlehome@users.noreply.github.com>

* fix

* update

* fix

* fix ci

* fix ci

* Initial plan

* test: add test_chat_with_response_max_tokens to test_EB_VL_Lite_serving.py

Co-authored-by: yuanlehome <23653004+yuanlehome@users.noreply.github.com>

* test: add disable-thinking case to test_chat_with_response_max_tokens

Co-authored-by: yuanlehome <23653004+yuanlehome@users.noreply.github.com>

* test: add both reasoning_max_tokens and response_max_tokens case

Co-authored-by: yuanlehome <23653004+yuanlehome@users.noreply.github.com>

* fix ci

* fix ci

* fix ci

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: yuanlehome <23653004+yuanlehome@users.noreply.github.com>
 2026-02-25 21:36:50 +08:00
YuBaoku e18397134a [Others] Update FASTDEPLOY_VERSION to 2.5.0-dev 2026-02-25 20:12:09 +08:00
YuBaoku fa8a2e32c8 [CI] Add test for prefix caching L2 swap (#6507) 2026-02-25 19:56:01 +08:00
zhupengyang a303eacf62 [XPU] support norm before rope (#6475) 2026-02-25 18:43:44 +08:00
Yuqiang Ge 1f931e05cd [CI] Add retry logic for pip install in iluvatar CI script (#6500) 2026-02-25 16:01:41 +08:00
Wanglongzhi2001 14ea7243e1 [Feature] support mm_processor_kwargs for flexible model 2026-02-25 14:34:33 +08:00
jackyYang6 a29ee57e15 [Feature] Support ThinkingBudget Logits processor to control thinking content length (#6367) 
* feat: add thinking budget logits processor

* add unittest

* fix pre-commit

* add unittest

* docs: clarify operator-level vs logits processor usage and conflict guidance

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
 2026-02-25 14:17:09 +08:00
YuBaoku 1405d7d5d7 [CI] Pin gunicorn version to 25.0.3 (#6497) 2026-02-25 09:52:22 +08:00
Longzhi Wang 22566168c3 [Feature] support qkv&gate linear fusion (#6455) 
* [Feature] support qkv&gate linear fusion

* add test
 2026-02-24 15:20:29 +08:00
jackyYang6 38c3e02470 fix paddleformers fallback (#6465) 2026-02-23 15:29:13 +08:00
Yonghua Li e2332a1112 [BugFix] fix num_cpu_blocks computation (#6438) 
* [BugFix] fix num_cpu_blocks computation

* [fix] fix syntax and log

* [fix] pre-commit

* [fix] use getattr

* [fix] ci test
 2026-02-13 11:05:14 +08:00
kevin 52edf5e9b3 fix mtp acceptance rate decline (#6470) 2026-02-12 19:56:10 +08:00
sunxin 51f812aaa4 fix empty get_padding_offset (#6462) 2026-02-12 12:34:23 +08:00
AIbin 0eb87467f8 [BugFix]fix RL bug about blockwisefp8 (#6466) 
* fix RL bug about blockwisefp8

* fix  moe same bug

* fix RL FP8 bug
 2026-02-12 09:15:29 +08:00
YuBaoku 9d72332aca [CI] Optimize unittest and fix title format (#6464) 
* [CI] Optimize unit test duration and fix PR title format
 2026-02-11 20:48:56 +08:00
Divano ba3b142ff7 [Others] add objgraph to test out of memory (#6456) 2026-02-11 20:17:20 +08:00
Zhang Yulong 96bfa0d5b9 [benchmark] Update benchmark_serving.py (#6467) 2026-02-11 20:10:46 +08:00
JYChen 40c952e7b5 fix deepgemm import (#6451) 
Co-authored-by: Jiaxin Sui <95567040+plusNew001@users.noreply.github.com>
 2026-02-11 20:10:01 +08:00
Jiaxin Sui e40fb16912 Revert "[XPU] change base XPU docker image (#6411)" (#6427) 
This reverts commit 32bd40a192.
 2026-02-11 16:31:54 +08:00
zhupengyang 4a8c54926b [XPU] topk_method=noaux_tc (#6355) 2026-02-11 16:12:20 +08:00
kesmeey e4e3a71e7b [CI] 【Hackathon 10th Spring No.22】功能模块 fastdeploy/cache_manager/cache_transfer_manager.py 单测补充 (#6157) 
* Add comprehensive test coverage for cache_transfer_manager.py

* Fix code style: add newline at end of file

* fix: update cache transfer manager tests for branch 22 interface changes

* fix: resolve test errors for cache transfer manager

* fix: update cache transfer manager tests for branch 22 interface changes

* style: apply pre-commit formatting to tests/cache_manager/test_cache_transfer_manager.py

* Run codestyle: format tests/cache_manager/test_cache_transfer_manager.py and related fixes

* Update test_cache_transfer_manager.py

* Format cache transfer manager tests

* Update cache transfer manager tests

* Update unit test coverage workflow

---------

Co-authored-by: CSWYF3634076 <wangyafeng@baidu.com>
 2026-02-11 11:23:57 +08:00
CSWYF3634076 7380bfb476 [BugFix]fix console log metrics waitting queue count (#6432) 
* [BugFix]fix console log metrics waitting queue count

* [BugFix]fix console log metrics waitting queue count unittest
 2026-02-11 10:51:49 +08:00
YuBaoku 390d0f2d77 [CI] Fix cherry-pick automation (#6448) 
* [CI] Fix cherry-pick automation
 2026-02-10 22:45:29 +08:00
YuBaoku a918738b8f [CI] Optimize cherry-pick automation (#6445) 2026-02-10 21:48:13 +08:00
Jiang-Jia-Jun 19849a0e9b Fix formatting in README_EN.md for v2.3 release 2026-02-10 20:32:15 +08:00
Jiang-Jia-Jun 3f9fcec8bd Update FastDeploy release notes in README_CN.md 2026-02-10 20:32:03 +08:00
Jiang-Jia-Jun a54b92448b Update README for version 2.4 2026-02-10 20:28:17 +08:00
Jiang-Jia-Jun 9d1fb17dc8 Update README_EN.md 2026-02-10 20:19:06 +08:00
Jiang-Jia-Jun f7e1b9355e Update README_EN.md 2026-02-10 20:18:04 +08:00