mirror of
https://github.com/vllm-project/vllm.git
synced 2025-10-20 14:53:52 +08:00
[XPU][Triton]add xpu config in triton_reshape_and_cache_flash (#25643)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
@ -137,7 +137,7 @@ def triton_reshape_and_cache_flash(
|
||||
|
||||
# heuristics instead of autotuning
|
||||
TILE_SIZE = min(2048, triton.next_power_of_2(n))
|
||||
if torch.version.hip:
|
||||
if torch.version.hip or torch.version.xpu:
|
||||
num_stages = 4
|
||||
num_warps = 8
|
||||
else: # cuda
|
||||
|
Reference in New Issue
Block a user