Nick HillandKimi Code e30559b58f [Core] Skip JIT monitor when JIT warmup is disabled (#58590) ...

Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Kimi Code <noreply@moonshot.cn>

2026-09-24 12:08:16 -07:00

..

attention

[Perf][Attention] Bound FlashInfer prefill dequantization scratch (#57918)

2026-09-24 10:42:08 -04:00

core

[Bugfix][V1] Reject encoder-cache hits with mismatched embedding counts (#57696)

2026-09-24 08:40:47 +00:00

engine

[MRV2] Validate MRV2 entrypoint logits processors (#57728)

2026-09-24 09:07:26 +00:00

executor

[AuxOutput] Add block-keyed storage for routed-expert outputs (#45635)

2026-09-21 10:25:05 +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

hisparse

[Bugfix][HiSparse][NIXL] Import full blocks without tail prefill on D (#57049)

2026-09-17 15:26:10 -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

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

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

metrics

[Bugfix][Metrics] Do not log a 0.0% prefix cache hit rate before any query (#54990)

2026-09-17 18:19:13 +00:00

pool

[Pooling] Improve BGE-M3 sync pooling throughput by up to 3.13% (#53464)

2026-08-24 08:33:32 -04:00

sample

[Dependency] Upgrade FlashInfer version to 0.7.0 (#58069)

2026-09-23 22:45:23 -07:00

simple_kv_offload

[Bugfix][KV Offload] Skip non-prefix-cacheable groups in SimpleCPUOffload (GLM-5.3-Flash kpool tail and QSA) (#56810)

2026-09-20 10:58:55 +00:00

spec_decode

[Perf] Remove CPU-GPU sync in heterogeneous vocabulary speculative decoding (#57396)

2026-09-22 18:34:19 -04:00

structured_output

[BugFix][Core] Make the structured-output grammar poll non-blocking (#55931)

2026-09-22 14:39:47 +03:00

watermarking

[MRV2][XPU] use xpu sample kernel in mrv2 sampler (#57277)

2026-09-21 13:24:41 +08:00

worker

[Core] Skip JIT monitor when JIT warmup is disabled (#58590)

2026-09-24 12:08:16 -07:00

__init__.py

…

cudagraph_dispatcher.py

Add pydocstyle to the ruff rules (#52136)

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

kv_cache_interface.py

[Feat][Model] Support encoder-side SWA-bounded replay for DeepSeek-V4.1-Flash (#56227)

2026-09-18 15:01:24 -07:00

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

[AuxOutput] Add block-keyed storage for routed-expert outputs (#45635)

2026-09-21 10:25:05 +00:00

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

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

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