dongmao zhang c459536b0f [PD] bug fix: Update status if nixl receiver send a a dummy req. (#6720)

2025-05-29 00:01:56 -07:00

..

base

[PD] Add support for different TP sizes per DP rank (#5922)

2025-05-12 13:55:42 -07:00

common

[PD] Make bootstrap code common between NIXL and Mooncake (#6473)

2025-05-27 12:47:38 -07:00

fake

[PD] Add doc and simplify sender.send (#6019)

2025-05-21 21:22:21 -07:00

mooncake

[PD] Remove Unnecessary Exception Handling for FastQueue.get() (#6712)

2025-05-28 11:18:24 -07:00

nixl

[PD] bug fix: Update status if nixl receiver send a a dummy req. (#6720)

2025-05-29 00:01:56 -07:00

decode_schedule_batch_mixin.py

[PD] Support structured output (#6560)

2025-05-23 21:49:00 -07:00

decode.py

[PD] Handle P/D failure and reconnect without affecting other instances (#6263)

2025-05-26 19:21:01 -07:00

kv_events.py

[Metrics] Add KV events publishing (#6098)

2025-05-19 14:19:54 -07:00

mini_lb.py

[Bugfix] Fix ChatCompletion endpoint of mini_lb when stream is set (#6703)

2025-05-28 21:33:36 +08:00

prefill.py

[PD] Handle P/D failure and reconnect without affecting other instances (#6263)

2025-05-26 19:21:01 -07:00

utils.py

[PD Perf] replace Queue to FastQueue (#6649)

2025-05-28 01:37:51 -07:00