Jundong Liu ff45ac078e [Feature] Use paddle.compat.enable_torch_proxy in fastdeploy/__init__.py (#5211) ...

* test feature

* fix xgrammar

* fix paddleformer

* try whitelist

* manual patch PaddlePaddle/Paddle#76706 for test

* remove triton version

* add comment

* Update scripts/run_ci_xpu.sh

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

* remove use-triton-in-paddle in requirement.txt

---------

Co-authored-by: Nyakku Shigure <sigure.qaq@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

2025-12-16 11:05:30 +08:00

..

benchmarks

…

cache_manager

[Optimization] support mm prefill batch (#5313)

2025-12-11 22:21:14 +08:00

demo

[PD Disaggregation] Add timestamp for analyzing splitwise deployment (#5317)

2025-12-08 10:08:44 +08:00

distributed

allow 0-dim tensor into ar (#5451)

2025-12-09 16:53:35 +08:00

engine

[BugFix] reschedule_preempt_task append waiting & PREEMPTED blocksize (#5506)

2025-12-12 17:43:29 +08:00

entrypoints

[Feature] Support for request-level speculative decoding metrics monitoring. (#5518)

2025-12-12 12:22:18 +08:00

eplb

[BugFix] fix cuda-python requirement (#5261)

2025-11-27 13:58:18 +08:00

input

[Feature]Optimization of Thinking Pattern Framework (#4302)

2025-12-10 16:17:06 +08:00

inter_communicator

[Optim] Improve task-checking performance in engine-worker-queue (#5376)

2025-12-11 10:33:32 +08:00

logger

[Log] Add trace log and add loggingInstrumentor tool (#4692)

2025-11-17 11:08:57 +08:00

metrics

[Feature] Support for request-level speculative decoding metrics monitoring. (#5518)

2025-12-12 12:22:18 +08:00

model_executor

[BugFix] fix dynamic c8 in v1 loader (#5562)

2025-12-15 04:07:54 -08:00

multimodal

[Bug Fix] process transparent image (#4807)

2025-11-05 17:15:24 +08:00

output

Fix bug for caching output when preempted (#5502)

2025-12-15 17:25:35 +08:00

platforms

[Feature] support flash_mask_attention backend (#5134)

2025-11-28 10:12:16 +08:00

plugins

[BugFix]Fix plugin loading logic and logging messages (#4909)

2025-12-05 19:25:01 +08:00

reasoning

[Feature]Optimization of Thinking Pattern Framework (#4302)

2025-12-10 16:17:06 +08:00

rl

[BugFix] fix instability after clearing weight (#5493)

2025-12-11 10:22:35 +08:00

router

[PD Disaggregation] Unify the disaggregation info and the pd communication (#5438)

2025-12-09 14:44:59 +08:00

scheduler

[BugFix] fix mix splitwise pickle load error (#5488)

2025-12-10 19:05:50 +08:00

spec_decode

[XPU] refactor of block_attn param 'pos_emb_type' (#5511)

2025-12-12 14:30:09 +08:00

splitwise

add check health in FD (#5534)

2025-12-15 15:14:45 +08:00

trace

[Log] Add trace log and add loggingInstrumentor tool (#4692)

2025-11-17 11:08:57 +08:00

transformer_utils

…

worker

[Metax] fix GetStopFlagsMulti kernel crash issue (#5556)

2025-12-15 01:56:20 -08:00

__init__.py

[Feature] Use paddle.compat.enable_torch_proxy in fastdeploy/__init__.py (#5211)

2025-12-16 11:05:30 +08:00

collect_env.py

…

config.py

[Metax] fix release2.4 and support cudagraph (#5547)

2025-12-15 14:23:33 +08:00

envs.py

add check health in FD (#5534)

2025-12-15 15:14:45 +08:00

import_ops.py

…

stop.sh

[PD Disaggregation] Support Qwen3-MoE use PD + EP inference. (#4691)

2025-11-06 10:32:15 +08:00

test.yaml

…

utils.py

[Feature] [Benchmark]: add ZMQ-based FMQ implementation and benchmark tools (#5418)

2025-12-08 22:04:49 +08:00