Isotr0pyandShanshan Shen 8352b2427f [Multimodal] Optimize encoder cudagraph padding logic (#58925) ...

Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>

2026-10-08 03:38:09 +00:00

..

attention

[ROCm][Perf][GLM-5.3-Flash] BF16 splitk kernel for sparse MLA decode (#58584)

2026-10-07 21:37:51 -05:00

core

[Bugfix][DSv4.1] Skip SWA bounded replay for KV loads that carry the window (#59197)

2026-10-07 15:28:42 -07:00

engine

[BugFix] Pick the DP world-group port at bind time via the coordination store (#51018)

2026-10-08 02:30:35 +00:00

executor

[Core] Bound execute_dummy_batch RPC waits by the execute-model timeout (#60398)

2026-10-08 01:22:04 +00:00

fault_tolerance

[Bugfix][FT] Pass stateless process-group timeouts explicitly (#58611)

2026-09-29 03:14:02 +00:00

hisparse

[Perf][HiSparse] Cache per-request residency instead of rescanning every page each step (#60083)

2026-10-06 13:04:55 -04:00

kv_hints

[Feature] Add first-class KV hints request envelope for programmatic KV management (#53423)

2026-09-21 09:56:11 -07:00

kv_offload

[Bugfix][KV Offload] Restore KVCR construction through the secondary-tier factory (#58088)

2026-10-07 21:36:57 +02:00

metrics

[Metrics] Expose cached prompt tokens by cache tier (#56318)

2026-10-06 14:52:05 -04:00

pool

[Bugfix][Pooling] Handle multimodal cache misses without crashing (#58975)

2026-10-02 10:14:33 -04:00

sample

[CPU][Perf] Add vectorized Sampler Kernel (#53913)

2026-09-30 15:16:28 +08:00

simple_kv_offload

[Bugfix][KV Offload] Honor speculative cacheability in SimpleCPU (#60071)

2026-10-06 14:25:08 +02:00

spec_decode

[PCP][DCP] Support DCP target model with non-DCP Dspark (#56723)

2026-09-26 18:12:35 -04:00

structured_output

[Bugfix][Structured Output] Flag multi-branch allOf as unsupported for xgrammar (#59061)

2026-10-06 17:01:04 +04:00

watermarking

[watermark] compatibility validation (#56801)

2026-10-05 14:37:13 -04:00

worker

[Multimodal] Optimize encoder cudagraph padding logic (#58925)

2026-10-08 03:38:09 +00:00

__init__.py

…

cudagraph_dispatcher.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

kv_cache_interface.py

[Attention] Add UltraQuant 4-bit KV cache backend (FlyDSL D=256) (#57057)

2026-10-06 20:42:52 +00:00

kv_cache_layout.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

kv_cache_spec_registry.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

outputs.py

[Feature][Spec Decode] Support sampling mask replay for MRV2 MTP (#59359)

2026-10-01 13:51:39 +08:00

request.py

[Feature] Add first-class KV hints request envelope for programmatic KV management (#53423)

2026-09-21 09:56:11 -07:00

serial_utils.py

[Feature] Per-row candidate IDs for prefill token scoring (M2 of #56860) (#56984)

2026-10-03 14:17:09 +00:00

utils.py

[Rust Frontend] Expose gRPC port in Python vllm serve (#59659)

2026-10-02 08:14:37 +00:00