lizexu123 9cb08e71e8 add support QWQ enable_thinking (#2706) ...

* add support QWQ enable_thinking

* add stream=True

* fix stream=true

* fix qwen

---------

Co-authored-by: lizexu <lizexu@baidu.com>

2025-07-04 20:55:23 +08:00

..

cache_manager

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

demo

[Sync] Update to latest code (#2679)

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

distributed

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

engine

[feat] support fa3 backend for pd disaggregated (#2695)

2025-07-03 22:33:27 +08:00

entrypoints

[RL] update reschedule finish reason (#2709)

2025-07-04 13:47:36 +08:00

input

[Sync] Update to latest code (#2679)

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

inter_communicator

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

metrics

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

model_executor

Extract eh_proj Layer from ParallelLMHead for MTP to Avoid Weight Transposition Issue (#2707)

2025-07-04 14:15:04 +08:00

output

[Bug] fix logger format (#2689)

2025-07-03 19:58:03 +08:00

platforms

[feat] support fa3 backend for pd disaggregated (#2695)

2025-07-03 22:33:27 +08:00

reasoning

add support QWQ enable_thinking (#2706)

2025-07-04 20:55:23 +08:00

rl

Update dynamic_weight_manager.py

2025-07-03 15:55:22 +08:00

scheduler

[Sync] Update to latest code (#2679)

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

spec_decode

Extract eh_proj Layer from ParallelLMHead for MTP to Avoid Weight Transposition Issue (#2707)

2025-07-04 14:15:04 +08:00

splitwise

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

worker

support chunk_prefill in MTP (#2705)

2025-07-04 11:55:48 +08:00

__init__.py

[feature]add fd whl version info (#2698)

2025-07-04 14:12:42 +08:00

config.py

[feat] support fa3 backend for pd disaggregated (#2695)

2025-07-03 22:33:27 +08:00

download_model.py

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

envs.py

[Sync] Update to latest code (#2679)

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

import_ops.py

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

stop.sh

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

test.yaml

[Sync] Update to latest code (#2679)

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

utils.py

[feature]add fd whl version info (#2698)

2025-07-04 14:12:42 +08:00