Sahil KadadekarandClaude Fable 5 55da232db6 [Bugfix] Pad Mamba page size instead of scaling block_size in unify_kv_cache_spec_page_size (#45207) ...

Signed-off-by: Sahil170595 <147995121+Sahil170595@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

2026-07-07 22:01:34 +00:00

..

sched

[Bugfix][Spec Decode] Skip uniform spec-decode padding for diffusion models (#47464)

2026-07-07 09:25:12 +00:00

__init__.py

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

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

block_pool.py

[1/N][Core] add partial prefix cache primitives (#45939)

2026-06-21 23:43:10 -07:00

encoder_cache_manager.py

[Perf] Improve multimodal item handling from O(n) to O(log n) per step (#44212)

2026-06-03 11:00:26 +00:00

kv_cache_coordinator.py

[Bugfix][Core] Fix host memory leak from undrained new_block_ids (#44490)

2026-07-07 07:32:55 +00:00

kv_cache_manager.py

[Model] Support Unlimited OCR (#46564)

2026-06-27 23:09:18 -07:00

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] Pad Mamba page size instead of scaling block_size in unify_kv_cache_spec_page_size (#45207)

2026-07-07 22:01:34 +00:00

single_type_kv_cache_manager.py

[Bugfix][Core] Fix host memory leak from undrained new_block_ids (#44490)

2026-07-07 07:32:55 +00:00