Wentao YeandNick Hill 3e440786af [Feature] Fully support for async scheduling + PP, 30.8% E2E throughput improvement, 31.8% TPOT improvement (#32618) ...

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>

2026-01-28 20:30:32 +00:00

..

sched

[Feature] Fully support for async scheduling + PP, 30.8% E2E throughput improvement, 31.8% TPOT improvement (#32618)

2026-01-28 20:30:32 +00:00

__init__.py

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

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

block_pool.py

[V1][Hybrid] Mamba Prefix Caching with align mode (#30877)

2026-01-23 09:56:48 -08:00

encoder_cache_manager.py

[EncoderCacheManager] Remove unnecessary copy (#32800)

2026-01-24 14:28:57 +00:00

kv_cache_coordinator.py

[V1][Hybrid] Mamba Prefix Caching with align mode (#30877)

2026-01-23 09:56:48 -08:00

kv_cache_manager.py

[V1][Hybrid] Mamba Prefix Caching with align mode (#30877)

2026-01-23 09:56:48 -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] Assign page_size_padded when unifying kv cache spec. (#32283)

2026-01-14 20:10:01 +00:00

single_type_kv_cache_manager.py

Add flake8-implicit-str-concat rules to Ruff (#33191)

2026-01-28 04:56:10 +00:00