Michael Goinandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> e3fe212eaf [Bugfix] Generalize KV block zeroing to AttentionSpec (#51749) ...

Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

2026-08-11 12:13:09 -04:00

..

sched

[Perf] Adaptive budget for spec scheduled input tokens, ~60% better Kimi K3 DSpark TTFT (#51725)

2026-08-10 20:52:21 -07:00

__init__.py

[V1] Implement vLLM V1 [1/N] (#9289)

2024-10-22 01:24:07 -07:00

block_pool.py

[BugFix][Core] free_blocks: restore prepend (LIFO) reuse order when prefix caching is off (#51482)

2026-08-11 03:56:25 +00:00

encoder_cache_manager.py

Encoder cache extension hooks (#48218)

2026-07-24 02:52:00 -07:00

kv_cache_coordinator.py

[BugFix] Handle per-group prefix-hit divergence for hybrid models with KV connector (#48425)

2026-07-22 17:19:11 -07:00

kv_cache_manager.py

[BugFix] Preserve divergent FA hits with external Mamba state (#51468)

2026-08-08 20:20:16 +08:00

kv_cache_metrics.py

[Core][Observability] Add KV cache residency metrics (#27793)

2025-12-01 18:27:53 +00:00

kv_cache_utils.py

[BugFix][KV Cache] Fix hybrid prefix caching with hidden-state extraction (#51108)

2026-08-06 06:42:37 +00:00

single_type_kv_cache_manager.py

[Bugfix] Generalize KV block zeroing to AttentionSpec (#51749)

2026-08-11 12:13:09 -04:00