Jialin Ouyangandyewentao256 0c11617ff1 [Core] Use KVCacheBlock as much as possible instead of dict[block_id, KVCacheBlock] (#24830) ...

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

2025-10-03 13:35:54 -07:00

..

__init__.py

Implement Async Scheduling (#19970)

2025-07-14 23:01:46 -07:00

test_async_scheduler.py

[Spec Decode] Make propose_draft_token_ids non-blocking for lower TTFT (#23041)

2025-08-18 17:20:38 -07:00

test_encoder_cache_manager.py

[Multimodal] Remove legacy multimodal fields in favor of MultiModalFeatureSpec (#24548)

2025-09-12 21:42:23 +08:00

test_kv_cache_utils.py

[Hybrid Allocator] Support full attention with different hidden size (#25101)

2025-10-03 13:35:53 -07:00

test_prefix_caching.py

[Core] Use KVCacheBlock as much as possible instead of dict[block_id, KVCacheBlock] (#24830)

2025-10-03 13:35:54 -07:00

test_scheduler_e2e.py

[Misc] unify variable for LLM instance (#20996)

2025-07-21 12:18:33 +01:00

test_scheduler.py

[Chore] Cleanup guided namespace, move to structured outputs config (#22772)

2025-09-18 09:20:27 +00:00

test_single_type_kv_cache_manager.py

[Core] Use KVCacheBlock as much as possible instead of dict[block_id, KVCacheBlock] (#24830)

2025-10-03 13:35:54 -07:00

utils.py

[Core] Use sha256 bytes instead of BlockHash to reduce GC overhead (#23673)

2025-09-08 21:34:37 -07:00