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

..

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

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

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

demo

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

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

distributed

[BugFix] 0 not into cuda graph to save memory (#5426)

2025-12-08 16:47:44 +08:00

engine

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

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

entrypoints

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

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

eplb

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

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

input

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

2025-12-09 10:53:40 +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

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

FA3 support qwen3 (#5441)

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

multimodal

[Bug Fix] process transparent image (#4807)

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

output

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

2025-12-08 10:08:44 +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

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

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

rl

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

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

router

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

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

scheduler

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

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

spec_decode

fix mtp prefix_cache dy-c8 bug (#5390)

2025-12-05 19:03:19 +08:00

splitwise

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

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

trace

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

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

transformer_utils

[Feature] support pool (#3827)

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

worker

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

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

__init__.py

remove fastsafetensors (#5371)

2025-12-04 19:22:04 +08:00

collect_env.py

feat: add support for API usage with multimodal models (#4548)

2025-10-28 20:23:46 +08:00

config.py

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

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

envs.py

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

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

import_ops.py

fix import error (#2944)

2025-07-22 14:06:01 +08:00

stop.sh

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

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

test.yaml

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

utils.py

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

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