Isotr0py 6aa5b18e1d [v1] Add encoder-only/cross attention support to Triton Attention backend (#31406) ...

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

2026-01-06 00:00:23 +08:00

..

attention

[v1] Add encoder-only/cross attention support to Triton Attention backend (#31406)

2026-01-06 00:00:23 +08:00

core

[Misc] Various code simplifications (#31666)

2026-01-04 18:35:56 -08:00

engine

[BugFix] Async scheduling: handle model forward errors more cleanly (#31611)

2026-01-04 11:04:37 -08:00

executor

[BugFix] Fix async scheduling for pooling models (#31584)

2025-12-31 14:48:51 -08:00

kv_offload

CPU KV Offloading: Use more CUDA streams (#29013)

2025-12-14 23:50:45 +00:00

metrics

[Metrics] Model FLOPs Utilization estimation (#30738)

2025-12-18 01:40:51 +00:00

pool

[BugFix] Fix async scheduling for pooling models (#31584)

2025-12-31 14:48:51 -08:00

sample

[BugFix] Fix logprobs with spec decode and modified logits (#30846)

2025-12-18 19:58:28 -08:00

spec_decode

[Misc] Various code simplifications (#31666)

2026-01-04 18:35:56 -08:00

structured_output

[Misc] Various code simplifications (#31666)

2026-01-04 18:35:56 -08:00

worker

[Misc] Various code simplifications (#31666)

2026-01-04 18:35:56 -08:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

cudagraph_dispatcher.py

[BugFix] Fix assert batch_descriptor.num_tokens == num_tokens_padded (#30173)

2025-12-09 10:36:12 -05:00

kv_cache_interface.py

[Model] Add support for openPangu moe model (#28775)

2025-12-30 08:11:38 -08:00

outputs.py

[BugFix] Fix async scheduling for pooling models (#31584)

2025-12-31 14:48:51 -08:00

request.py

[Minor] Various small code cleanups/simplifications (#31508)

2025-12-29 22:42:06 -08:00

serial_utils.py

[Model] Move multimodal_cpu_fields definition to field config (#30181)

2025-12-06 13:40:02 +00:00

utils.py

[BugFix] Fix async scheduling + chunked prefill + preemption (#28787)

2025-11-17 06:46:46 +08:00