李泳桦 d18a637a17 [feat] add metrics for yiyan adapter (#3219) ...

* [feat] add metrics for yiyan adapter

* [fix] fix metrics num_requests_waiting and num_requests_running

* [fix] fix metrics gpu_cache_usage_perc

* [refactor] change where requests_number increases

* [chore] rename xxx_block_num as xxx_gpu_block_num, and update their values accordingly

* [chore] delete useless code

2025-08-21 16:58:10 +08:00

..

cache_manager

[feat] add metrics for yiyan adapter (#3219)

2025-08-21 16:58:10 +08:00

demo

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

distributed

update flake8 version to support pre-commit in python3.12 (#3000)

2025-07-24 01:43:31 -07:00

engine

[feat] add metrics for yiyan adapter (#3219)

2025-08-21 16:58:10 +08:00

entrypoints

[Feature] optimize expert parallel (#3196)

2025-08-05 17:34:24 +08:00

input

[Feature] remove dependency on enable_mm and refine multimodal's code (#3014)

2025-08-01 20:01:18 +08:00

inter_communicator

[Bug fix] Fix bug for d blocks not enough (#3479)

2025-08-21 11:36:16 +08:00

metrics

[feat] add metrics for yiyan adapter (#3219)

2025-08-21 16:58:10 +08:00

model_executor

[Bug fix] Fix bug for seq_len_encoder is 1 (#3467)

2025-08-19 15:21:32 +08:00

multimodal

[Feature] remove dependency on enable_mm and refine multimodal's code (#3014)

2025-08-01 20:01:18 +08:00

output

[feat] add metrics for yiyan adapter (#3219)

2025-08-21 16:58:10 +08:00

platforms

native top_p_sampling (#2901)

2025-07-22 14:09:59 +08:00

plugins

【Feature】add fd plugins && rm model_classes (#3123)

2025-08-03 19:53:20 -07:00

reasoning

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

rl

【Feature】support qwen3 name_mapping (#3179)

2025-08-04 01:34:07 -07:00

scheduler

[Feature] Support batched tokens for EP (#3415)

2025-08-18 11:43:36 +08:00

spec_decode

[Feature] Support mtp ep in fd (#3340)

2025-08-11 21:49:44 +08:00

splitwise

[feat] add metrics for yiyan adapter (#3219)

2025-08-21 16:58:10 +08:00

worker

[Feature] Support batched tokens for EP (#3415)

2025-08-18 11:43:36 +08:00

__init__.py

【Feature】add fd plugins && rm model_classes (#3123)

2025-08-03 19:53:20 -07:00

config.py

[BugFix]Fix ep size (#3092)

2025-07-30 21:03:12 +08:00

envs.py

[Feature] Support batched tokens for EP (#3415)

2025-08-18 11:43:36 +08:00

import_ops.py

fix import error (#2944)

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

stop.sh

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

test.yaml

[Sync] Update to latest code (#2679)

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

utils.py

[Feature] remove dependency on enable_mm and refine multimodal's code (#3014)

2025-08-01 20:01:18 +08:00