Andrew Xia 25aba2b6a3 [gpt-oss] Add IncompleteDetails to ResponsesRepsonse (#24561) ...

Signed-off-by: Andrew Xia <axia@meta.com>

2025-09-15 13:07:55 -07:00

..

attention

[XPU] Set consistent default KV cache layout (#24745)

2025-09-15 18:09:34 +08:00

core

[gpt-oss] Add IncompleteDetails to ResponsesRepsonse (#24561)

2025-09-15 13:07:55 -07:00

engine

[gpt-oss] Add IncompleteDetails to ResponsesRepsonse (#24561)

2025-09-15 13:07:55 -07:00

executor

[P/D]kv_output_aggregator support P TP > D TP (#23917)

2025-09-15 11:36:06 +02:00

metrics

[Spec Decoding]Support Spec Decoding Metrics in DP Mode (#24049)

2025-09-14 21:11:09 +00:00

pool

[Performance] V1 Pooling Models E2E Performance Optimization (#23162)

2025-08-21 13:26:09 +00:00

sample

fix some typos (#24167)

2025-09-10 06:21:23 -07:00

spec_decode

[Spec Decoding]Support Spec Decoding Metrics in DP Mode (#24049)

2025-09-14 21:11:09 +00:00

structured_output

[Doc]: fix typos in Python comments (#24093)

2025-09-02 21:05:45 -07:00

worker

[Chore] Minor simplification for non-PP path (#24810)

2025-09-13 17:41:36 -07:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

cudagraph_dispatcher.py

[CI] Fix linting error on main (#23835)

2025-08-28 06:52:01 -07:00

kv_cache_interface.py

Add the support for the qwen3 next model (a hybrid attention model). (#24526)

2025-09-11 15:32:09 +08:00

outputs.py

[Perf][V1] Fully overlap model execution (#23569)

2025-09-05 18:20:17 -07:00

request.py

[Multimodal] Remove legacy multimodal fields in favor of MultiModalFeatureSpec (#24548)

2025-09-12 21:42:23 +08:00

serial_utils.py

[Refactor] Define MultiModalKwargsItems separate from MultiModalKwargs (#23053)

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

utils.py

Allow users to specify kv cache memory size (#21489)

2025-09-11 13:41:07 +00:00