Jiangyun Zhu 5728da11ea Revert #26113 "[Frontend] CompilationConfig overhaul (#20283): deprecate use_inductor in favor of backend, simplify custom_ops" (#26472) ...

Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>

2025-10-09 05:43:55 -07:00

..

__init__.py

[Bugfix] Fix vllm bench ... on CPU-only head nodes (#25283)

2025-10-08 16:06:42 +00:00

cpu.py

Revert #26113 "[Frontend] CompilationConfig overhaul (#20283): deprecate use_inductor in favor of backend, simplify custom_ops" (#26472)

2025-10-09 05:43:55 -07:00

cuda.py

[Hybrid]: Decouple Kernel Block Size from KV Page Size (#24486)

2025-10-08 23:43:39 -07:00

interface.py

[Kernel] Centralize platform kernel import in current_platform.import_kernels (#26286)

2025-10-08 20:25:31 +00:00

rocm.py

[Hardware][AMD] Enable FlexAttention backend on ROCm (#26439)

2025-10-09 06:20:18 +00:00

tpu.py

[Kernel] Centralize platform kernel import in current_platform.import_kernels (#26286)

2025-10-08 20:25:31 +00:00

xpu.py

[Kernel] Centralize platform kernel import in current_platform.import_kernels (#26286)

2025-10-08 20:25:31 +00:00