Li, JiangandGitHub 63f1fde277 [Hardware][CPU] Support chunked-prefill and prefix-caching on CPU (#10355) ...

Signed-off-by: jiang1.li <jiang1.li@intel.com>

2024-11-20 10:57:39 +00:00

..

__init__.py

[Platform][Refactor] Extract func get_default_attn_backend to Platform (#10358)

2024-11-19 11:22:26 +08:00

cpu.py

[Hardware][CPU] Support chunked-prefill and prefix-caching on CPU (#10355)

2024-11-20 10:57:39 +00:00

cuda.py

[Misc] Upgrade to pytorch 2.5 (#9588)

2024-10-27 09:44:24 +00:00

hpu.py

[Platform][Refactor] Extract func get_default_attn_backend to Platform (#10358)

2024-11-19 11:22:26 +08:00

interface.py

[Platform][Refactor] Extract func get_default_attn_backend to Platform (#10358)

2024-11-19 11:22:26 +08:00

neuron.py

[Neuron] [Bugfix] Fix neuron startup (#9374)

2024-10-22 12:51:41 +00:00

openvino.py

[Platform][Refactor] Extract func get_default_attn_backend to Platform (#10358)

2024-11-19 11:22:26 +08:00

rocm.py

[Platform][Refactor] Extract func get_default_attn_backend to Platform (#10358)

2024-11-19 11:22:26 +08:00

tpu.py

[6/N] torch.compile rollout to users (#10437)

2024-11-19 10:09:03 -08:00

xpu.py

[Platforms] Refactor xpu code (#10468)

2024-11-19 22:52:13 -08:00