apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-05-10 01:21:55 +08:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity
4,467 Commits 31 Branches 17 Tags
14a64e9b3b3fb8210ceecba1c93022bebbdb0d1d
Commit Graph

4467 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
zccjjj 14a64e9b3b [XPU] change XPU EP interface from xDeepEP to paddle (#5706) 
* add ENV VAR to controll low lantency buffer
 2026-01-21 18:23:45 +08:00
K11OntheBoat 490a6551dc rename params of normalization layer (#6133) 
Co-authored-by: “liuruian” <liuruian@baidu.com>
 2026-01-21 17:18:35 +08:00
lizexu123 1f96028bea [BugFix] fix python3.12 v0_loader (#6132) 2026-01-21 16:12:11 +08:00
yzwu 837ddca273 [Iluvartar][CI] Fix the error max_tokens_per_expert referenced before assignment (#6083) 2026-01-21 16:01:29 +08:00
yinwei 85d995100a Update Dummy Run To Suppport Mutil-Batch Execution (#6123) 2026-01-21 14:20:44 +08:00
Cheng Yanfei 9ee0156cc3 add HPU tensorwise_fp8 readme (#6091) 2026-01-21 11:48:22 +08:00
MingkunZhang 7e04067663 [Metax][CI] restore 'moe_expert_dispatch' outputs (#6130) 2026-01-21 10:33:09 +08:00
YuBaoku c991fda54c [CI] Enable 4-GPU e2e test in nightly and fix docker_tag_build (#6128) 2026-01-20 22:44:29 +08:00
lizexu123 f4902fe42d [BugFix] fix wint2 (#6109) 
* fix

* fix

* fix
 2026-01-20 21:46:21 +08:00
yinwei 5385d51808 [XPU]XPU FD Release/2.4 Note 2026-01-20 20:38:34 +08:00
Copilot dcb20c1a2a [WIP] Add directory guide to mkdocs configuration (#6121) 
* Initial plan

* Add PaddleFormers Backend documentation to mkdocs.yml navigation

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

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
 2026-01-20 19:51:27 +08:00
luukunn 56e22a7ddc [Docs]fix doc (#6119) 
* fix doc

* fix doc
 2026-01-20 19:46:05 +08:00
yinwei 51a8a2ed57 [XPU] Support CudaGraph(add block attn cuda_graph support) (#6116) 
* add block attn cuda_graph support
 2026-01-20 19:33:11 +08:00
jackyYang6 00a6a73431 docs: fix pre-commit error of markdown (#6100) 2026-01-20 19:32:05 +08:00
ChowMingSing bf60e103b6 [CI]Fix test case (#6111) 2026-01-20 17:47:44 +08:00
Ryan dda27e50f5 [Graph Optimization] remove static_op_get_block_shape_and_split_kv_block from cudagraph (#6081) 
* rm static_op_get_block_shape_and_split_kv_block from cudagraph

* update max_capture_shape

* fallback: zeros -> empty to avoid coverage check

* check graph_opt_config exists

* add max_capture_shape_dy2st && full_cuda_graph: false -> true in 28B vl test

* add use_cudagraph flag to control step_use_cudagraph
 2026-01-20 14:05:18 +08:00
zhupengyang 45ebb2efb4 [XPU] support plugin model (#6092) 2026-01-20 13:00:09 +08:00
jackyYang6 988e0bc338 [Feature] Add PaddleFormers fallback backend (#5999) 
* feat(paddleformers): add dense text model fallback backend

* docs(paddleformers): add user guide and fix code review issues

* add fallback unit test

* precommit format

* fix pre-commit

* fix: address code review feedback

* docs: add PaddleFormers backend documentation (EN) and simplify installation

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
 2026-01-19 21:50:50 +08:00
GoldPancake 879e45f6b3 fix compute logits problem (#6093) 2026-01-19 20:12:14 +08:00
xiegegege e22c4e29bb [CE]add paddleocr config yaml (#6097) 2026-01-19 20:07:42 +08:00
Jingfeng Wu 7d44009f39 [FDConfig] transfer metrics_port (#6056) 
* transfer metrics_port

* transfer metrics_port
 2026-01-19 19:58:57 +08:00
cmcamdy 211dd81ca7 add pd+mtp ci (#6090) 2026-01-19 19:21:24 +08:00
Jiaxin Sui e0d15a2ded [XPU][CI] Xpu ci update (#6089) 
* add xpu ci case

* add xpu ci case

* add xpu ci case

* Change runner from XPU-P800-8Card to XPU-P800

* Remove cache queue port from test_pd_03b_tp1.py

Removed cache queue port arguments from test cases.

* Remove cache queue port from test_pd_21b_tp2.py

Removed cache queue port arguments from test cases.

* Update README with PYTHONPATH setup instructions

Added instructions for setting PYTHONPATH in CI scripts.
 2026-01-19 16:09:09 +08:00
ChowMingSing 496cc23089 [CI]Fix test cases failing under Python 3.12 (#6059) 
* 修复python3.12下测试用例错误

* 修复python3.12下测试用例错误

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
 2026-01-19 15:41:12 +08:00
sunxin a4144e0b8e [Optimization] Avoid unnecessary penalty computation (#6078) 2026-01-19 15:24:12 +08:00
GoldPancake 05fbd89a8e [Speculative Decoding][Bugfix] Fix MTP logprob issues caused by max_num_logprobs (#6084) 2026-01-19 14:55:36 +08:00
ddchenhao66 3685474799 [XPU] xpu support mm prefill batch (#6072) 
Co-authored-by: ddchenhao66 <dhaochen163.com>
 2026-01-19 14:36:35 +08:00
sunxin 9dc1c74d36 fix opt qknorm (#6080) 2026-01-19 12:07:20 +08:00
YuBaoku ac6fa6d725 [CI] Add 4-GPU e2e test job (#6082) 2026-01-19 10:42:14 +08:00
kevin 0e0eaa1c57 [BugFix] fix mm revert bug (#6061) 
* fix mm revert bug

* update code
 2026-01-16 08:13:34 -08:00
Jiaxin Sui 70a962df53 [XPU][CI] XPU CI refactor (#6053) 
* add xpu ci case

* add xpu ci case

* add xpu ci case

* Change runner from XPU-P800-8Card to XPU-P800
 2026-01-16 20:57:58 +08:00
GoldPancake b917b56aca [Bugfix] Fix logprob issues caused by max_num_logprobs (#6067) 2026-01-16 04:40:18 -08:00
周周周 97f96e34ca only update self.exist_prefill_task_signal in v0 (#6064) 
* commit

* commit

* commit

---------

Co-authored-by: xiaoluomi <1037819816@qq.com>
 2026-01-16 20:11:55 +08:00
MingkunZhang 0d372e4fb2 [Metax][CI] update jenkins github action version (#6065) 2026-01-16 15:06:14 +08:00
GoldPancake bda38aa519 [Speculative Decoding] Support MTP for GLM-4.5-Air (#6047) 
* glm mtp
* add spec neox partial rope
 2026-01-16 14:35:24 +08:00
qwes5s5 b2a2e11551 [Feature] Support stopping the inference for the corresponding request in the online service after a disconnection request. (#5320) 
* request disconnect

* request disconnect

* fix bug

* fix bug--amend

---------

Co-authored-by: root <root@yq01-sys-rpm26xc1knu.yq01.baidu.com>
 2026-01-16 11:46:13 +08:00
周周周 8f035101ad initial commit (#6054) 
Co-authored-by: xiaoluomi <1037819816@qq.com>
 2026-01-16 10:49:38 +08:00
fxyfxy777 4c92035f2d [Feature] Unify fp8 block_wise quant ops (#5991) 
* quant stash

* blockwise_quant

* precommit

* rm tensor.cut

* tp ok

* add swiglu

* rm outdate code

* fix activate ut

* change baseline

* fix baseline error
 2026-01-15 05:50:37 -08:00
周周周 d38cd8b40b [UNITEST] add EP TP test_fused_moe CI (#5989) 2026-01-15 21:37:32 +08:00
guozhuangzhuang d2f1ec2b1b [XPU] fix(xpu_model_runner): reset seq_lens_encoder to 0 for decode role in PD splitwise mode (#6048) 
* fix(xpu_model_runner): reset seq_lens_encoder to 0 for decode role in PD splitwise mode

- Set seq_lens_encoder to 0 when splitwise_role is 'decode' during prefill processing
- This ensures proper continuation of decoding after P generate first token in PD disaggregated architecture
- Fixes potential sequence length inconsistency in PD splitwise deployment scenarios

* format
 2026-01-15 20:24:56 +08:00
freeliuzc 49617d9832 [Feature]Support tag phase token enforce generation (#6034) 
* support tag phase token enforce generation

* optimize note and some feature

* fix sampler unit test

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
 2026-01-15 03:59:55 -08:00
freeliuzc 17866c028e add more cases for attention unit test (#5931) 2026-01-15 19:52:35 +08:00
cmcamdy 59d8ae0a25 [XPU] Speculate Decoding + PD, benchmark fix (#6036) 
* fix mtp pd

* fix kernel

* fix code style

* fix kernel

* fix test / clear debug code

* fix test / clear debug code

* fix codestyle

* fix codestyle

* fix codestyle
 2026-01-15 19:19:03 +08:00
lizexu123 6619298b50 【Optim】Optimize grid dimensions using max_tokens_per_expert for MoE models (#6007) 
* update w4afp8

* build.sh ok

* support cuda_graph

* fix

* add test

* fix max_tokens_per_expert

* >=70

* fix

* compute_max_tokens_from_prefix_sum in w4afp8

* compute_max_tokens use cub
 2026-01-15 19:18:42 +08:00
Jiaxin Sui b0fc9cadb5 [XPU][CI] update paddle version (#6044) 
* Remove cache queue port from test configuration

Removed cache queue port configuration from test.

* Remove cache queue port from test_vl_model.py

Removed cache queue port argument from test configuration.

* Update test_w4a8.py

* Remove cache queue port from test_mtp.py

Removed cache queue port configuration from test.

* Remove cache queue port from test_logprobs_21b_tp4

Removed cache queue port configuration from test.

* Remove cache queue port from test configuration

Removed cache queue port configuration from test.

* Update test_ep4tp4_online.py

* Update run_xpu_ci_pytest.sh to comment out installations

Comment out PaddlePaddle installation and XVLLM download steps.
 2026-01-15 15:17:48 +08:00
Daci e10b51b8c6 [Feature] get_output_kv_signal blocking read mode & send_first_token (#5836) 
* get_output_kv_signal blocking read mode

* send first token before recycle

* xpu get_output_kv_signal blocking read mode

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
 2026-01-15 14:11:03 +08:00
Cheng Yanfei fbcccaa750 [Intel HPU] enable MoE EP for hpu (#5855) 
* enable HPU MoE EP

* MoE intermediate_scale stack

* enable loader_v1 esp for tensor_wise_fp8 TP or EP

* modify activation_scale name
 2026-01-15 13:08:00 +08:00
ming1753 7c56041272 [BugFix] fix PaddleOCR-VL illegal memory (#6042) 2026-01-14 20:07:43 -08:00
zhupengyang 24ffa7c991 [XPU] fix moe num_expert (#6014) 2026-01-15 10:49:36 +08:00
RAM b3f59fd9b5 [RL][CI] Support Async R3 And Add Accuracy Test (#5937) 
* add bs1 r3 test case

* async put

* r3 test case 1.0

* success run eb5

* refine test case

* pre-commit

* add eb45 & glm testcase

* format code

* add p2pstore requirements

* support only last turn

* R3 use worker log

* refine code &fix ci bug

* refine error mesg

* fix empty input bug

* Success set acc ci of eb45 and glm45

* refine code

* fix bug
 2026-01-14 04:25:06 -08:00