MOVZXandHinata fb52250c11 [Scheduler] Drop the one-victim preemption guard that upstream #49675 made dead ...

The cascade test now expects zero needless victims.

Co-Authored-By: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>

2026-10-09 20:01:26 +07:00

..

sched

[Scheduler] Drop the one-victim preemption guard that upstream #49675 made dead

2026-10-09 20:01:26 +07:00

__init__.py

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

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

block_pool.py

[Core][BugFix] Tag prefix-cache extra keys by source (#51899)

2026-09-29 18:24:59 -07:00

encoder_cache_manager.py

[Bugfix][V1] Reject encoder-cache hits with mismatched embedding counts (#57696)

2026-09-24 08:40:47 +00:00

kv_cache_coordinator.py

[Bugfix][Core] Exempt exactly the blocks an async KV load writes from zeroing (#59504)

2026-10-03 06:26:12 +00:00

kv_cache_manager.py

[QSA] Tag every raw-key ring row and validate it before pooling

2026-10-09 20:01:26 +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

[KV] Restore PP fix #54793 -- no KV tensors for another stage's layers

2026-10-09 19:55:23 +07:00

single_type_kv_cache_manager.py

[QSA] Tag every raw-key ring row and validate it before pooling

2026-10-09 20:01:26 +07:00