cctry 2ad9a243f5 Size KV pool after CUDA graph capture (opt-in) (#30157)

2026-07-07 12:05:01 -07:00

..

__init__.py

[mem_cache][1/N] refactor: split allocator.py into allocator/ subpackage (#26675)

2026-05-31 20:31:29 +08:00

base.py

Size KV pool after CUDA graph capture (opt-in) (#30157)

2026-07-07 12:05:01 -07:00

hisparse.py

[AMD] Enable HiSparse on ROCm (#26639)

2026-06-19 11:59:45 -07:00

mamba.py

feat(mem_cache): unified memory pool for hybrid Mamba / SWA models (#29678)

2026-07-01 13:21:59 -07:00

paged.py

[AMD] Support triton backend decode context parallel for Qwen3.5 (#25090)

2026-06-23 17:35:56 -07:00

swa.py

Size KV pool after CUDA graph capture (opt-in) (#30157)

2026-07-07 12:05:01 -07:00

token.py

[mem_cache][1/N] refactor: split allocator.py into allocator/ subpackage (#26675)

2026-05-31 20:31:29 +08:00