We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent f2a2039 commit f08c4f1Copy full SHA for f08c4f1
vllm_ascend/quantization/w8a8_dynamic.py
@@ -141,8 +141,8 @@ def fused_experts_with_mc2(
141
local_rank = torch.distributed.get_rank(group=ep_group)
142
all_to_all_group_size = torch.distributed.get_world_size(ep_group)
143
144
- world_szie = torch.distributed.get_world_size()
145
- tp_size = world_szie // all_to_all_group_size
+ world_size = torch.distributed.get_world_size()
+ tp_size = world_size // all_to_all_group_size
146
tp_rank = rank % tp_size
147
148
stage1_kwargs = {
0 commit comments