Kunshang Ji 7caec10e7b [XPU]avoid circular import during XPU init (#23017) ...

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

2025-08-16 05:16:34 +00:00

..

__init__.py

[TPU] Support Pathways in vLLM (#21417)

2025-07-30 10:02:12 -07:00

cpu.py

[gpt-oss] Enable gpt-oss on ampere (#22714)

2025-08-12 03:21:44 -07:00

cuda.py

[Core] Allow full cudagraph with separate attention routines and orthogonal to compilation, add support for FA2 and FlashInfer (#20059)

2025-08-15 10:01:39 -04:00

interface.py

[Core] Allow full cudagraph with separate attention routines and orthogonal to compilation, add support for FA2 and FlashInfer (#20059)

2025-08-15 10:01:39 -04:00

neuron.py

[Refactor]Abstract Platform Interface for Distributed Backend and Add xccl Support for Intel XPU (#19410)

2025-07-07 04:32:32 +00:00

rocm.py

[Core] Allow full cudagraph with separate attention routines and orthogonal to compilation, add support for FA2 and FlashInfer (#20059)

2025-08-15 10:01:39 -04:00

tpu.py

[Core] Allow full cudagraph with separate attention routines and orthogonal to compilation, add support for FA2 and FlashInfer (#20059)

2025-08-15 10:01:39 -04:00

xpu.py

[XPU]avoid circular import during XPU init (#23017)

2025-08-16 05:16:34 +00:00