Andrii SkliarandAndrii Skliar deb148e730 [Mamba] Add FlashInfer ReplaySSM support for MTP (#52928) ...

Signed-off-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: Andrii Skliar <askliar@nvidia.com>

2026-09-30 21:41:17 +00:00

..

attention

[Mamba] Add FlashInfer ReplaySSM support for MTP (#52928)

2026-09-30 21:41:17 +00:00

core

[Bugfix][Core] Fix mamba prefill checkpoint block reservation and prompt-end eviction in align mode (#59175)

2026-09-30 21:26:54 +00:00

engine

[Frontend][RL] Align sleep-mode API responses and operation metrics (#52864)

2026-09-29 23:16:38 -07:00

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] Adopt GPU prefix copies after the hit's allocation (#59282)

2026-09-30 15:43:09 -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

[Core] Rework scheduler skipped_waiting queue (#58947)

2026-09-28 20:03:16 +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

[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

[watermarking] add context deduplication support to speculative decoding (#56807)

2026-09-30 12:22:10 -04:00

worker

[watermarking] add context deduplication support to speculative decoding (#56807)

2026-09-30 12:22:10 -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

[KV-Offloading][TP] : Expand replicated_layout detection to multi-group MLA (#57652)

2026-09-30 09:11:03 -04:00

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] Add fixed-token prefill scoring (#54335)

2026-09-28 07:50:09 -07:00

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

[Bugfix][Rust Frontend] Fix startup with config-only model (#58643)

2026-09-29 10:11:53 +00:00