3 people ca0df1f122 [Bugfix][Core] Exempt exactly the blocks an async KV load writes from zeroing (#59504) ...

Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Codex <noreply@openai.com>

2026-10-03 06:26:12 +00:00

..

attention

[GLM 5.3 Perf] Enable fused multi-step decode, 13.3% E2E throughput improvement for concurrency 1 (#57443)

2026-10-02 20:05:27 -04:00

core

[Bugfix][Core] Exempt exactly the blocks an async KV load writes from zeroing (#59504)

2026-10-03 06:26:12 +00:00

engine

[Bugfix][Frontend] Avoid generation for empty streaming input (#59015)

2026-10-02 18:48:43 +00:00

executor

[Core] Bound draft-token RPC waits by the execute-model timeout (#58779)

2026-09-26 00:40:22 +00:00

fault_tolerance

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

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

hisparse

[Bugfix][HiSparse] Fix MTP acceptance collapse under FULL graphs with a saturated GPU pool (#59309)

2026-10-01 23:04:21 -07:00

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][Core] Exempt exactly the blocks an async KV load writes from zeroing (#59504)

2026-10-03 06:26:12 +00:00

metrics

[Metrics][P/D] Add KV-fetch stage gauges for async KV loads (#58874)

2026-10-02 01:24:33 +00:00

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

[Core][BugFix] Tag prefix-cache extra keys by source (#51899)

2026-09-29 18:24:59 -07:00

spec_decode

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

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

structured_output

[Model] Engine based plamo3 parser (#56575)

2026-09-29 05:17:42 +00:00

watermarking

[Bugfix][Watermarking] Keep draft prompt lengths valid under CUDA graphs (#59779)

2026-10-02 14:32:11 -04:00

worker

[GLM 5.3 Perf] Enable fused multi-step decode, 13.3% E2E throughput improvement for concurrency 1 (#57443)

2026-10-02 20:05:27 -04:00

__init__.py

…

cudagraph_dispatcher.py

Add pydocstyle to the ruff rules (#52136)

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

kv_cache_interface.py

[Bugfix][HiSparse] Size the KV cache from the groups HiSparse allocates (#59450)

2026-10-02 04:11:55 +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

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

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

utils.py

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

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