Saddss 588db18362 [Bugfix] Two-phase KV allocation for cross-group prefix cache hits (supersedes #33775) (#44409) ...

Signed-off-by: Saddss <2872669061@qq.com>

2026-06-15 22:39:59 +08:00

..

sched

[V1][Spec Decode] Add Dynamic SD (#32374)

2026-06-14 00:14:27 -07:00

__init__.py

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

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

block_pool.py

[Prefix Caching] DeepSeekv4 - Support selective prefix-cache retention for sliding-window KV cache (#43447)

2026-06-04 00:48:31 -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] Two-phase KV allocation for cross-group prefix cache hits (supersedes #33775) (#44409)

2026-06-15 22:39:59 +08:00

kv_cache_manager.py

[Core] Add kvcache watermark to reduce preemptions (#44594)

2026-06-11 08:27:31 -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

[Metrics] Add group-aware KV cache capacity to vllm:cache_config_info (#42206)

2026-06-12 11:49:44 +00:00

single_type_kv_cache_manager.py

[Bugfix] Two-phase KV allocation for cross-group prefix cache hits (supersedes #33775) (#44409)

2026-06-15 22:39:59 +08:00