aoshen02andClaude Opus 5.5 5e56e9af2a [Feature] Release the CUDA graph pool on sleep (#59160) ...

Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

2026-10-04 01:13:10 +00:00

..

attention

[DCP] Enable TokenSpeed MLA with block-interleaved DCP (#59462)

2026-10-03 17:26:07 +00:00

core

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

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

cudagraph

[Feature] Release the CUDA graph pool on sleep (#59160)

2026-10-04 01:13:10 +00:00

determinism

[Distributed] Enable custom all-reduce under VLLM_BATCH_INVARIANT (#58623)

2026-10-02 02:25:48 +00:00

distributed

[Bugfix][CI] Widen DBO+DP+EP GSM8K accuracy margin on ROCm (#59700)

2026-10-01 23:37:36 +00:00

e2e

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

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

ec_connector

[EPD] Support metadata-only audio inputs (#57887)

2026-09-23 09:03:50 +08:00

engine

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

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

executor

Disable mypy arg-type and assignment checks in tests (#59428)

2026-09-30 15:18:50 +00:00

fault_tolerance

[Feature] Add fault tolerance framework (simplified) for DP+EP external LB deployments (#44428)

2026-07-25 11:49:09 -04:00

kv_connector

[Bugfix][MoRIIO] Keep discovery heartbeats running while workers hold the GIL (#59441)

2026-10-03 14:55:18 +00:00

kv_offload

Disable mypy arg-type and assignment checks in tests (#59428)

2026-09-30 15:18:50 +00:00

logits_processors

[MyPy][3/N] Fix MyPy errors in test groups (part 3) (#55939)

2026-09-30 11:06:07 +00:00

metrics

[Metrics] Add --custom-histogram-buckets to override histogram bucket families (#48867)

2026-10-01 01:03:39 +00:00

sample

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

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

shutdown

Add pydocstyle to the ruff rules (#52136)

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

simple_kv_offload

[Core] Remove deprecated mamba_cache_mode "all" (#58997)

2026-10-01 02:59:37 -07:00

spec_decode

[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

streaming_input

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

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

structured_output

Disable mypy arg-type and assignment checks in tests (#59428)

2026-09-30 15:18:50 +00:00

tracing

[CI] Fix segfault in tracing test (#47299)

2026-07-01 14:00:37 +00:00

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

…

test_kv_cache_spec_registry.py

Add pydocstyle to the ruff rules (#52136)

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

test_oracle.py

[Docs] Clean up speculators docs (#34065)

2026-02-18 13:48:11 -08:00

test_outputs.py

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

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

test_request.py

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

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

test_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

test_tensor_ipc_queue.py

[CI] Stabilize tensor IPC multiprocessing tests (#50804)

2026-08-12 10:16:43 +08:00

utils.py

Add pydocstyle to the ruff rules (#52136)

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