Unverified Commit 1c160841 authored by Wentao Ye's avatar Wentao Ye Committed by GitHub
Browse files

[Bug] Fix DeepSeek-V2.5-1210-FP8 issue (#27267)


Signed-off-by: default avataryewentao256 <zhyanwentao@126.com>
parent 4ca13a86
...@@ -511,13 +511,19 @@ def cutlass_moe_fp8( ...@@ -511,13 +511,19 @@ def cutlass_moe_fp8(
assert quant_config is not None assert quant_config is not None
if quant_config.a1_scale is not None: if quant_config.a1_scale is not None:
assert quant_config.per_act_token_quant == quant_config.a1_scale.numel() != 1 assert quant_config.per_act_token_quant == (quant_config.a1_scale.numel() != 1)
if quant_config.a2_scale is not None: if quant_config.a2_scale is not None:
assert quant_config.per_act_token_quant == quant_config.a2_scale.numel() != 1 assert quant_config.per_act_token_quant == (quant_config.a2_scale.numel() != 1)
assert quant_config.w1_scale is None or ( if quant_config.w1_scale is not None:
quant_config.per_out_ch_quant == (quant_config.w1_scale.size(1) == w1_q.size(1)) if quant_config.per_out_ch_quant:
) assert quant_config.w1_scale.dim() > 1 and quant_config.w1_scale.size(
1
) == w1_q.size(1)
else:
assert (
quant_config.w1_scale.dim() == 1 or quant_config.w1_scale.size(1) == 1
)
num_experts = global_num_experts if global_num_experts != -1 else w1_q.size(0) num_experts = global_num_experts if global_num_experts != -1 else w1_q.size(0)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment