Woosuk Kwon 98a3a81024

[ROCm] Add attention sink to use_rocm_custom_paged_attention (#22329) ...

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

Co-authored-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
Co-authored-by: Minseok Lee <47620120+minseokl@users.noreply.github.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>

2025-08-05 23:30:38 -07:00

..

__init__.py

[TPU] Support Pathways in vLLM (#21417)

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

cpu.py

[CPU] Enable shared-memory based pipeline parallel for CPU backend (#21289)

2025-07-21 09:07:08 -07:00

cuda.py

[V1] port xformers backend to v1 (#21342)

2025-08-05 10:04:46 -07:00

interface.py

[V1] port xformers backend to v1 (#21342)

2025-08-05 10:04:46 -07:00

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

[ROCm] Add attention sink to use_rocm_custom_paged_attention (#22329)

2025-08-05 23:30:38 -07:00

tpu.py

Fix kv_cache_dtype handling for out-of-tree HPU plugin (#21302)

2025-07-21 23:35:14 -07:00

xpu.py

[XPU] use ZE_AFFINITY_MASK for device select on xpu (#21815)

2025-07-30 03:56:14 +00:00