Wentao Ye b34474bf2c [Feature] Support async scheduling + PP (#32359) ...

Signed-off-by: yewentao256 <zhyanwentao@126.com>

2026-01-15 12:06:23 -05:00

..

sched

[Feature] Support async scheduling + PP (#32359)

2026-01-15 12:06:23 -05:00

__init__.py

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

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

block_pool.py

[Prefix Cache] Include lora_name in BlockStored event for deterministic KV-cache reconstruction (#27577)

2025-12-30 00:17:16 +00:00

encoder_cache_manager.py

[Core][MM] Optimize encoder cache manager by operating with embeddings only (#30475)

2025-12-16 14:18:17 -08:00

kv_cache_coordinator.py

[Feat][Core] Support multiple KV cache groups in Hybrid KV Coordinator (#31707)

2026-01-09 10:53:20 -08:00

kv_cache_manager.py

[Core][Hybrid allocator + connector] Support hybrid allocator + kv cache connector (#30166)

2025-12-26 18:25:46 -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

[Model] Add support for openPangu moe model (#28775)

2025-12-30 08:11:38 -08:00