kevin 5d42f19e0a [BugFix][Scheduler] Fix can_schedule_block_num_threshold calculation (#6541) ...

* fix mtp acceptance rate decline

* [BugFix][Scheduler] Fix can_schedule_block_num_threshold calculation

Fix the calculation of can_schedule_block_num_threshold in
ResourceManagerV1. The original formula using need_prefill_tokens
could lead to incorrect threshold values. Now directly use
num_chunk_new_block for accurate block scheduling.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-28 16:23:18 +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

[BugFix] Fix storage_backend_type comparison bug in cache_transfer_manager.py (#6514)

2026-02-26 19:32:24 +08:00

demo

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

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

distributed

[Feature] Add Deterministic Inference Support (#6476)

2026-02-26 19:31:51 -08:00

engine

[BugFix][Scheduler] Fix can_schedule_block_num_threshold calculation (#6541)

2026-02-28 16:23:18 +08:00

entrypoints

[BugFix] Enable control socket disable option in API server (#6545)

2026-02-28 10:35:35 +08:00

eplb

fix eplb weight updating (#5529)

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

golang_router

[Feature] Fix counter release logic & update go-router download URL (#6280)

2026-02-04 15:02:38 +08:00

input

[OP][Feature] 统一 limit_thinking_content_length CUDA 算子，支持回复长度限制与注入序列 (#6493)

2026-02-25 21:36:50 +08:00

inter_communicator

[BugFix] fix cache transfer tasks failure after cache cleared (#6202)

2026-02-08 15:33:56 +08:00

logger

[Feature] Add Deterministic Inference Support (#6476)

2026-02-26 19:31:51 -08:00

metrics

[Metrics] Support cpu-cache-block-num (#6390)

2026-02-09 10:27:56 +08:00

model_executor

[XPU] support warmup with ep & remove apply_tp_fused_op (#6289)

2026-02-28 15:40:36 +08:00

multimodal

[BugFix] fix dyc8 cache bug (#5958)

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

output

[Speculative Decoding] Support suffix decoding (#6403)

2026-02-26 11:42:05 +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] Support GLM MTP RL Model (#6267)

2026-02-04 20:14:35 +08:00

router

router support divided roolout (#6150)

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

scheduler

Revert "[Optimize] Optimize ttft for ep (#6098)" (#6402)

2026-02-09 19:01:23 +08:00

spec_decode

[Feature] GPU Memory Optimization and Retirement of V0 Scheduler (#6407)

2026-02-28 15:07:43 +08:00

splitwise

Revert "[Optimize] Optimize ttft for ep (#6098)" (#6402)

2026-02-09 19:01:23 +08:00

trace

set tracelogger stacklevel=2 (#5766)

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

transformer_utils

[Feature] support pool (#3827)

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

usage

[Feature]Report FD statistical information (#5646)

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

worker

[XPU] support warmup with ep & remove apply_tp_fused_op (#6289)

2026-02-28 15:40:36 +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

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

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

config.py

[XPU] support warmup with ep & remove apply_tp_fused_op (#6289)

2026-02-28 15:40:36 +08:00

envs.py

update FD_USAGE_STATS_SERVER (#6524)

2026-02-27 13:28:57 +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

[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

[Others] add objgraph to test out of memory (#6456)

2026-02-11 20:17:20 +08:00