Lucas WilkinsonandClaude 57bd0ed441 [5/N][KV-Cache Layout Refactor] Backend-published KV packing via customize_spec (#51704) ...

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>

2026-08-14 09:47:55 -04:00

..

sched

[Model Runner V2][Spec Decode] Add KV cache support for multi-layer MTP (#50062)

2026-08-13 16:22:29 -07:00

__init__.py

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

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

block_pool.py

[Core] Clearer comments in BlockPool.free_blocks() (#52076)

2026-08-12 20:36:08 -07:00

encoder_cache_manager.py

[Core] Configure custom encoder cache managers from VllmConfig (#51251)

2026-08-13 16:08:01 +08:00

kv_cache_coordinator.py

[Model Runner V2][Spec Decode] Add KV cache support for multi-layer MTP (#50062)

2026-08-13 16:22:29 -07:00

kv_cache_manager.py

[Model Runner V2][Spec Decode] Add KV cache support for multi-layer MTP (#50062)

2026-08-13 16:22:29 -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

[Model Runner V2][Spec Decode] Add KV cache support for multi-layer MTP (#50062)

2026-08-13 16:22:29 -07:00

single_type_kv_cache_manager.py

[5/N][KV-Cache Layout Refactor] Backend-published KV packing via customize_spec (#51704)

2026-08-14 09:47:55 -04:00