lizexu123 b0cf2c4b7a [Feature] Support prefill batch inference for pooling models. (#5436) ...

* fix multi-inputs

* fix threshold

* fix threshold

* fix

* support multi-batch

* add tests

* fix test

* test

* fix

2025-12-09 16:21:00 +08:00

..

batch_invariant

[Deterministic] Move paddle version batch invariant pkg to Fastdeploy (#4763)

2025-12-01 11:25:48 +08:00

benchmarks

[CLI]Update parameters in bench latecy cli tool and fix collect-env cli tool (#4558)

2025-10-24 16:46:45 +08:00

cache_manager

Revert "[CI] 【Hackathon 9th Sprint No.33】NO.33 功能模块单测补充 (#5056)" (#5286)

2025-11-28 10:48:35 +08:00

ce

[BugFix] fix mm cudagraph (#5266)

2025-12-09 11:51:00 +08:00

ci_use

[CI] Allow occasional distributed worker exit_code (#5341)

2025-12-03 10:56:59 +08:00

distributed

[New][RL] Support Rollout Routing Replay (#5405)

2025-12-05 22:06:26 +08:00

e2e

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

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

engine

[Engine] [Feature] Refactor async_llm:cross-process with EngineService，based on zmq communication (#4868)

2025-12-09 10:53:40 +08:00

entrypoints

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

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

eplb

[Feature] support eplb in api_server (#4782)

2025-11-24 20:22:29 +08:00

graph_optimization

[Docs] Add License in Unittest (#4957)

2025-11-12 10:44:09 +08:00

input

[CI]【Hackathon 9th Sprint Example NO 16】功能模块 fastdeploy/input/ernie4_5_vl_processor/process.py 单测补充 (#5264)

2025-12-08 14:30:15 +08:00

inter_communicator

[Engine] [Feature] Refactor async_llm:cross-process with EngineService，based on zmq communication (#4868)

2025-12-09 10:53:40 +08:00

layers

Remove CUDA ERROR 9 of inputs of get_padding_offset kernel (#5440)

2025-12-09 14:17:30 +08:00

logger

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

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

metrics

[BugFix][Metrics] Fix Prometheus Multiprocess Metrics Issues and Add ZMQ Communication Metrics (#5185)

2025-11-27 15:05:09 +08:00

model_executor

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

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

model_loader

[CI] fix test_model_cache (#4982)

2025-11-12 20:26:49 +08:00

multimodal

[CI]【Hackathon 9th Sprint No.56】NO.56 功能模块 fastdeploy/multimodal/utils.py 单测补充 (#4954)

2025-11-14 10:37:27 +08:00

operators

Remove CUDA ERROR 9 of inputs of get_padding_offset kernel (#5440)

2025-12-09 14:17:30 +08:00

output

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

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

platforms

[CI] Add Unittest (#5187)

2025-11-25 11:00:34 +08:00

plugins

[Feature] support pool (#3827)

2025-09-22 14:09:09 +08:00

pooling

[Feature] Support prefill batch inference for pooling models. (#5436)

2025-12-09 16:21:00 +08:00

quantization

[Quantization] Support w4afp8 MoE dynamic quantization (#5282)

2025-12-02 18:56:16 +08:00

reasoning

[BugFix] Fix ernie_vl_reasoning_parsers.py 'end_token' to 'think_end_token' (#4805)

2025-11-06 11:28:55 +08:00

scheduler

[CI] Add Unittest (#5187)

2025-11-25 11:00:34 +08:00

splitwise

Revert "[CI] 【Hackathon 9th Sprint No.41】NO.41 功能模块单测补充 (#5062)" (#5291)

2025-12-02 13:43:13 +08:00

trace

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

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

utils

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

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

v1

[BugFix] fix async download bug (#5349)

2025-12-05 18:59:12 +08:00

woker

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

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

xpu_ci

[XPU] support ep4tp1+v1 loader (#5398)

2025-12-05 18:51:15 +08:00

conftest.py

[CI] fix test_model_cache (#4982)

2025-11-12 20:26:49 +08:00

cov_pytest.ini

[CI] disable test_schedule_output.py in unit_test (#5377)

2025-12-04 23:18:23 +08:00

utils.py

[Models] Add forward_meta to moe models' forward function (#5138)

2025-12-04 13:26:58 +08:00