huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-19 22:02:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

some minor fix (#3048)

Browse Source 
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
This commit is contained in:
Wang, Yi 2025-02-25 19:07:55 +08:00 committed by GitHub
parent cea9dbc971
commit d7a24c03cf
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
server/text_generation_server/layers/gptq/__init__.py
View File

@ -171,6 +171,7 @@ class GPTQWeightsLoader(WeightsLoader):
g_idx=g_idx, g_idx=g_idx,
bits=self.bits, bits=self.bits,
groupsize=self.groupsize, groupsize=self.groupsize,
use_awq_kernel=self.quantize == "awq",
use_exllama=use_exllama, use_exllama=use_exllama,
) )

2
server/text_generation_server/layers/moe/unquantized.py
View File

@ -85,6 +85,8 @@ class UnquantizedSparseMoELayer(nn.Module):
use_grouped_topk=self.n_expert_group is not None, use_grouped_topk=self.n_expert_group is not None,
num_expert_group=self.n_expert_group, num_expert_group=self.n_expert_group,
topk_group=self.topk_group, topk_group=self.topk_group,
scoring_func=self.scoring_func,
e_score_correction_bias=self.e_score_correction_bias,
) )
return fused_moe( return fused_moe(
x, x,