3 people e73ff24e31 [ROCM][KERNEL] Paged attention for V1 (#15720) ...

Signed-off-by: Aleksandr Malyshev <maleksan@amd.com>
Signed-off-by: root <root@banff-cyxtera-s65-4.amd.com>
Co-authored-by: Aleksandr Malyshev <maleksan@amd.com>
Co-authored-by: root <root@banff-cyxtera-s65-4.amd.com>

2025-04-02 19:48:00 -07:00

..

__init__.py

Remove openvino support in favor of external plugin (#15339)

2025-03-22 14:06:39 -07:00

cpu.py

[Bugfix] Fix failure to launch in Tensor Parallel TP mode on macOS. (#14948)

2025-03-28 10:13:41 +08:00

cuda.py

[Distributed] Add custom allreduce support for ROCM (#14125)

2025-03-31 22:49:12 -07:00

hpu.py

[platform] add base class for communicators (#13208)

2025-02-16 22:14:22 +08:00

interface.py

[bugfix] add supports_v1 platform interface (#15417)

2025-03-25 15:00:32 -04:00

neuron.py

[Neuron] Add Neuron device communicator for vLLM v1 (#14085)

2025-03-10 18:37:04 -07:00

rocm.py

[ROCM][KERNEL] Paged attention for V1 (#15720)

2025-04-02 19:48:00 -07:00

tpu.py

[bugfix] add supports_v1 platform interface (#15417)

2025-03-25 15:00:32 -04:00

xpu.py

[Misc][XPU] Use None as device capacity for XPU (#14932)

2025-03-17 01:22:14 -07:00