luukunn 6b47773bd6 [fix]Modify follow-up push parameters and Modify the verification method for thinking length (#4177) ...

* [fix]Modify follow-up push parameters and Modify the verification method for thinking length (#4086)

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* add completion_token_ids

* add logger

* fix reasoning_max_tokens ParameterError

* add unittest

* add unittest

* add unittest

* add unittest

* add unittest

* add unit test

* fix

2025-09-22 21:12:05 +08:00

..

cache_manager

[fix] initialize available_gpu_block_num with max_gpu_block_num (#4193)

2025-09-22 18:56:00 +08:00

demo

[Feature] Add AsyncTokenizerClient&ChatResponseProcessor with remote encode&decode support. (#3674)

2025-08-30 17:06:26 +08:00

distributed

Supports DP+TP+EP hybrid parallel deployment strategy (#3489)

2025-08-26 00:04:01 -07:00

engine

[fix] fix ep group all-reduce (#4140)

2025-09-18 10:34:49 +08:00

entrypoints

[fix]Modify follow-up push parameters and Modify the verification method for thinking length (#4177)

2025-09-22 21:12:05 +08:00

input

[fix]Modify follow-up push parameters and Modify the verification method for thinking length (#4177)

2025-09-22 21:12:05 +08:00

inter_communicator

[feat] support prefix cache clearing when /clear_load_weight is called (#4091)

2025-09-16 11:11:20 +08:00

logger

add error log to file (#3431)

2025-08-20 09:52:34 +08:00

metrics

Fixed the issue of metrics file conflicts between multiple instances … (#4010)

2025-09-10 13:48:24 +08:00

model_executor

[Executor] Adjust signal sending order in RL training (#3773) (#4066) (#4178)

2025-09-22 14:31:36 +08:00

multimodal

[Model]support qwen2_5_vl (#3557)

2025-08-29 18:28:39 +08:00

output

[Feature] Support mixed deployment with yiyan adapter in release22 (#3974)

2025-09-10 16:01:13 +08:00

platforms

【FIX】Change the name of sparse attn from moba to plas (#4006)

2025-09-10 10:04:29 +08:00

plugins

add reasoning parser plugin (#3820)

2025-09-03 11:17:13 +08:00

reasoning

[Feature] add tool parser (#3483)

2025-08-21 17:25:44 +08:00

rl

[Executor] Adjust signal sending order in RL training (#3773) (#4066) (#4178)

2025-09-22 14:31:36 +08:00

scheduler

[Feature] Support mixed deployment with yiyan adapter in release22 (#3974)

2025-09-10 16:01:13 +08:00

spec_decode

update hybrid-mtp-with-ngram (#3924)

2025-09-05 23:06:57 +08:00

splitwise

[Feature] Support mixed deployment with yiyan adapter in release22 (#3974)

2025-09-10 16:01:13 +08:00

worker

[Executor] Adjust signal sending order in RL training (#3773) (#4066) (#4178)

2025-09-22 14:31:36 +08:00

__init__.py

[BugFix] Fix default log level of paddleformers (#3376)

2025-08-14 11:36:24 +08:00

config.py

[fix] fix ep group all-reduce (#4140)

2025-09-18 10:34:49 +08:00

envs.py

[feat] support prefix cache clearing when /clear_load_weight is called (#4091)

2025-09-16 11:11:20 +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

[CP]Glm45 air 2.2 (#4073)

2025-09-15 18:52:58 +08:00