Dakai An dc0d318177 [Attention] Add FLASH_ATTN_MLA_SPARSE backend for Hopper sparse MLA (#46189) ...

Signed-off-by: Dakai An <dakaian108@gmail.com>

2026-06-24 09:33:10 +00:00

..

__init__.py

[Core] Ensure memory is pinned prior to async h2d copy (#45424)

2026-06-20 20:02:24 -07:00

cpu.py

[HARDWARE][POWER] Enable fp16 support for PowerPC (#46135)

2026-06-23 13:24:49 +00:00

cuda.py

[Attention] Add FLASH_ATTN_MLA_SPARSE backend for Hopper sparse MLA (#46189)

2026-06-24 09:33:10 +00:00

interface.py

Stop setting CUDA_VISIBLE_DEVICES internally in vLLM, add device_ids arg (#45026)

2026-06-20 13:38:10 -07:00

rocm.py

[ROCm][CI] Query total device memory via amdsmi to avoid HIP init (#46141)

2026-06-22 15:12:24 -05:00

tpu.py

[Refactor][TPU] Remove torch_xla path and use tpu-inference (#30808)

2026-01-07 16:07:16 +08:00

xpu.py

[Core] Ensure memory is pinned prior to async h2d copy (#45424)

2026-06-20 20:02:24 -07:00

zen_cpu.py

[ZenCPU] AMD Zen CPU Backend with supported dtypes via zentorch weekly (#39967)

2026-04-18 06:22:37 +00:00