ZiTian.Zhao e27d25a0dc

[fix] fix correct assertion syntax error in attention utils. (#22154) ...

Signed-off-by: zitian.zhao <zitian.zhao@tencentmusic.com>

2025-08-03 19:24:02 -07:00

..

attention

[fix] fix correct assertion syntax error in attention utils. (#22154)

2025-08-03 19:24:02 -07:00

core

[V1] [P/D] Refactor KV Connector Path (#21980)

2025-08-03 04:03:40 -07:00

engine

[BugFix] Improve internal DP load balancing (#21617)

2025-08-01 19:45:27 -07:00

executor

[executor] feat: add supports_pp attr to executors (#21786)

2025-08-03 18:04:45 +08:00

metrics

[BugFix] Improve internal DP load balancing (#21617)

2025-08-01 19:45:27 -07:00

pool

[Model][1/N] Support multiple poolers at model level (#21227)

2025-07-21 02:22:21 -07:00

sample

[Logs] Change flashinfer sampler logs to once (#21759)

2025-07-28 06:59:51 -07:00

spec_decode

[Meta] Official Eagle mm support, first enablement on llama4 (#20788)

2025-07-31 10:35:07 -07:00

structured_output

[Refactor][V1] Move outlines utils for V1 imports (#20878)

2025-07-14 00:58:35 -07:00

worker

[V1] [P/D] Refactor KV Connector Path (#21980)

2025-08-03 04:03:40 -07:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

2024-11-11 23:05:38 +00:00

kv_cache_interface.py

[KVCache] Make KVCacheSpec hashable (#21791)

2025-07-29 19:58:29 +08:00

outputs.py

[V1] [P/D] Refactor KV Connector Path (#21980)

2025-08-03 04:03:40 -07:00

request.py

Implement Async Scheduling (#19970)

2025-07-14 23:01:46 -07:00

serial_utils.py

[BugFix] Fix case where collective_rpc returns None (#22006)

2025-07-31 12:51:37 +00:00

utils.py

[BugFix] Improve internal DP load balancing (#21617)

2025-08-01 19:45:27 -07:00