Andy Lo 58ce8d12b7 [BugFix] Priority scheduling and spec tokens preemption (#28558) ...

Signed-off-by: Andy Lo <andy@mistral.ai>

2025-11-12 20:29:21 +00:00

..

sched

[BugFix] Priority scheduling and spec tokens preemption (#28558)

2025-11-12 20:29:21 +00:00

__init__.py

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

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

block_pool.py

[BugFix][LoRA] use adapter_id instead of id field of lora_request (#27728)

2025-11-03 10:08:08 +08:00

encoder_cache_manager.py

[Misc] Simplify max tokens in multimodal registry (#27500)

2025-10-24 23:56:01 -07:00

kv_cache_coordinator.py

[Core] Reuse empty block lists whenever possible in KVCacheBlocks to mitigate GC costs (#24964)

2025-10-14 12:58:43 -07:00

kv_cache_manager.py

[Core][Perf] Only invoke save_new_computed_blocks when computed blocks are not empty (#27799)

2025-10-30 19:47:30 +00:00

kv_cache_utils.py

[Chore]:Extract math and argparse utilities to separate modules (#27188)

2025-10-26 04:03:32 -07:00

single_type_kv_cache_manager.py

[Core][Hybrid allocator + connector 2/n] Unify remove_skipped_blocks by get_last_useful_token (#25431)

2025-11-06 00:12:00 +00:00