aditi-amd 6ef1efd51f [ROCm] Fix TurboQuant on ROCm: backend routing, flash-attn compat, int64 overflow (#39953) ...

Signed-off-by: aditi <aditi.rana@amd.com>

2026-04-17 13:08:37 -07:00

..

__init__.py

In-Tree AMD Zen CPU Backend via zentorch [1/N] (#35970)

2026-03-15 23:35:35 +00:00

cpu.py

[CPU] Refactor CPU affinity and memory management (#39781)

2026-04-17 21:01:08 +08:00

cuda.py

Fix TURBOQUANT backend selection in cuda.py (#40060)

2026-04-17 07:31:41 -07:00

interface.py

[Bugfix] Use is_integrated to detect UMA GPUs for memory reporting (#35356)

2026-04-13 11:07:40 -07:00

rocm.py

[ROCm] Fix TurboQuant on ROCm: backend routing, flash-attn compat, int64 overflow (#39953)

2026-04-17 13:08:37 -07:00

tpu.py

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

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

xpu.py

[XPU] use spawn multiproc method on xpu (#39671)

2026-04-16 14:42:07 +08:00

zen_cpu.py

[ZenCPU] Make PT Backport Patch Accessible to vLLM (#38205)

2026-04-10 08:29:35 +00:00