ddchenhao66 6d33d5e370 [Models][BugFix] shared experts and dense mlp layer do not require TP split (#6180) ...

Co-authored-by: ddchenhao66 <dhaochen163.com>

2026-01-28 18:58:19 +08:00

..

benchmarks

…

cache_manager

[RL] add version to the key of cache storage && refine raising error (#6160)

2026-01-27 10:47:46 +08:00

demo

…

distributed

Support setting communication groups in custom_allreduce and the all-to-all\transpose fused operator during the decoding phase. (#5917)

2026-01-12 14:09:39 +08:00

engine

[Bug fix] Fix multi modal fetch feature (#6095)

2026-01-28 18:02:26 +08:00

entrypoints

fix image gen (#6175)

2026-01-23 11:24:12 +08:00

eplb

fix eplb weight updating (#5529)

2025-12-19 14:30:32 +08:00

golang_router

[Feature] Add Golang-based Router for Request Scheduling and Load Balancing (#5882)

2026-01-07 21:28:08 +08:00

input

bug fix tool_calls (#6166)

2026-01-23 10:49:27 +08:00

inter_communicator

[RL] add pause, update_weights, resume interface for async RL (#6052)

2026-01-23 10:18:07 +08:00

logger

…

metrics

add token ratio metrics (#6236)

2026-01-27 17:00:49 +08:00

model_executor

[Models][BugFix] shared experts and dense mlp layer do not require TP split (#6180)

2026-01-28 18:58:19 +08:00

multimodal

[BugFix] fix dyc8 cache bug (#5958)

2026-01-08 19:25:47 -08:00

output

add token ratio metrics (#6236)

2026-01-27 17:00:49 +08:00

platforms

[Feature]Report FD statistical information (#5646)

2026-01-14 17:54:01 +08:00

plugins

【Optimization】update data_processor & add tool parser plugins (#6096)

2026-01-22 17:17:32 +08:00

reasoning

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

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

rl

[RL] add pause, update_weights, resume interface for async RL (#6052)

2026-01-23 10:18:07 +08:00

router

router support divided roolout (#6150)

2026-01-22 10:39:39 +08:00

scheduler

[RL] add pause, update_weights, resume interface for async RL (#6052)

2026-01-23 10:18:07 +08:00

spec_decode

[BugFix] Fix token_penalty kernel (#6069)

2026-01-28 12:03:05 +08:00

splitwise

[BugFix] fix mask_attn (#6214)

2026-01-26 07:46:51 -08:00

trace

set tracelogger stacklevel=2 (#5766)

2025-12-26 17:43:32 +08:00

transformer_utils

…

usage

[Feature]Report FD statistical information (#5646)

2026-01-14 17:54:01 +08:00

worker

[Others] Support constrained decoding when enable_thinking is false (#6248)

2026-01-28 00:05:17 -08:00

__init__.py

[Optimization] The pre- and post-processing pipeline do not perform dict conversion (#5494)

2026-01-22 00:50:52 +08:00

collect_env.py

…

config.py

[Loader] support dummy load weight (#6169)

2026-01-26 13:58:53 +08:00

envs.py

Support MXFP4 for GPT-OSS (#5435)

2026-01-22 14:21:01 +08:00

import_ops.py

[build] support build sm 80,86,89,90 to one whl package (#6173)

2026-01-26 11:30:02 +08:00

stop.sh

…

test.yaml

…

utils.py

Support MXFP4 for GPT-OSS (#5435)

2026-01-22 14:21:01 +08:00