[CPU] Use accelerator memory API in DiffusionGemma (#58964)
Signed-off-by: zhejiangxiaomai <zhenhui.zhao@intel.com> Co-authored-by: Li, Jiang <jiang1.li@intel.com>
This commit is contained in:
co-authored by
Li, Jiang <jiang1.li@intel.com>
parent
2407f405b5
commit
1668e5976d
@@ -1493,7 +1493,7 @@ class DiffusionSampler:
|
||||
# [tile * W, vocab] copies, so a tile is also bounded by free memory.
|
||||
widths_np = states.canvas_width_np[decode_slots_np]
|
||||
order = np.argsort(widths_np, kind="stable")
|
||||
free = current_platform.mem_get_info()[0] if num_decode > 0 else 0
|
||||
free = torch.accelerator.get_memory_info()[0] if num_decode > 0 else 0
|
||||
run_start = 0
|
||||
while run_start < num_decode:
|
||||
W = int(widths_np[order[run_start]])
|
||||
|
||||
Reference in New Issue
Block a user