kevin bf30f45738 [BugFix] fix vl performance bug (#5181) ...

* fix vl performance bug

* update code

* update code

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>

2025-11-26 21:06:52 +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

[Metrics] Update time_to_first_token to include tokenization & queue time, and remove redundant metrics (#4993)

2025-11-26 14:42:17 +08:00

demo

[PD Disaggregation] remove splitwise deployment on single node and refine the code (#4891)

2025-11-14 09:56:53 +08:00

distributed

fix import jit.marker.unified (#4622)

2025-10-28 22:11:03 +08:00

engine

[BugFix] fix vl performance bug (#5181)

2025-11-26 21:06:52 +08:00

entrypoints

[Feature] The 45VL supports prompt_token_ids + messages input. (#5148)

2025-11-25 23:11:44 +08:00

eplb

[Fix] fix eplb noaux (#5239)

2025-11-26 17:50:51 +08:00

input

fix prompt_token_ids is None in request dict (#5241)

2025-11-26 17:10:45 +08:00

inter_communicator

[Feature] support eplb in api_server (#4782)

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

logger

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

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

metrics

[Metrics] Update time_to_first_token to include tokenization & queue time, and remove redundant metrics (#4993)

2025-11-26 14:42:17 +08:00

model_executor

[BugFix] BF16 MoE Cutlass Backend Support EP (#5242)

2025-11-26 19:16:22 +08:00

multimodal

[Bug Fix] process transparent image (#4807)

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

output

[Metrics] Update time_to_first_token to include tokenization & queue time, and remove redundant metrics (#4993)

2025-11-26 14:42:17 +08:00

platforms

[Metax] adapt DeepSeek (#4498)

2025-10-24 10:14:53 +08:00

plugins

[Feature] add cli command serve (#4226)

2025-09-24 14:50:45 +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

[Feature] support eplb in api_server (#4782)

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

router

[PD Disaggregation] [Refine] Refine splitwise deployment (#5151)

2025-11-21 15:30:24 +08:00

scheduler

[Speculative Decoding][MTP]Update extract_mtp_weight script and optimize config (#5183)

2025-11-25 14:09:03 +08:00

spec_decode

[BugFix]Fix attention mask bug in D-Node of PD-split mode (#5245)

2025-11-26 17:56:28 +08:00

splitwise

[Optimization] Improve perf for fd response token with internal adapter (#4992)

2025-11-21 19:02:03 +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

check (#5237)

2025-11-26 17:07:26 +08:00

__init__.py

[BugFix] fix work metrics not returned by metrics api (#4912)

2025-11-25 19:12:29 +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

[BugFix] fix vl performance bug (#5181)

2025-11-26 21:06:52 +08:00

envs.py

[Feature] support eplb in api_server (#4782)

2025-11-24 20:22:29 +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] remove to_numpy (#5162)

2025-11-21 21:54:26 +08:00