Yong Hoon ShinandGitHub ad510309ee Override attention metadata for fast prefill in some KV sharing setups (#21590) ...

Signed-off-by: Yong Hoon Shin <yhshin@meta.com>

2025-07-30 08:54:15 -07:00

..

__init__.py

[V1] Implement Cascade Attention (#11635)

2025-01-01 21:56:46 +09:00

test_cascade_attention.py

[XPU] Use spawn with XPU multiprocessing (#20649)

2025-07-09 00:34:28 -07:00

test_correctness_sliding_window.py

[KVCache] Make KVCacheSpec hashable (#21791)

2025-07-29 19:58:29 +08:00

test_kv_sharing_fast_prefill.py

Override attention metadata for fast prefill in some KV sharing setups (#21590)

2025-07-30 08:54:15 -07:00

test_spec_decode.py

[Meta] Llama4 EAGLE Support (#20591)

2025-07-15 21:14:15 -07:00