biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Doc]: fix typos in Python comments (#24294)

Browse Source 
Signed-off-by: Didier Durand <durand.didier@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
This commit is contained in:
Didier Durand
2025-09-06 04:41:12 +02:00
committed by GitHub
parent 35efa70297
commit 35bf193864
12 changed files with 17 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/model_executor/layers/quantization/gptq_marlin.py
View File

@@ -469,7 +469,7 @@ class GPTQMarlinMoEMethod(FusedMoEMethodBase):
)
layer.register_parameter("w2_scales", w2_scales)
set_weight_attrs(w2_scales, extra_weight_attrs)
# dont shard the w2 scales when running act order
# don't shard the w2 scales when running act order
set_weight_attrs(w2_scales,
{"load_full_w2": self.quant_config.desc_act})
# up_proj scales
@@ -493,7 +493,7 @@ class GPTQMarlinMoEMethod(FusedMoEMethodBase):
)
layer.register_parameter("w2_qzeros", w2_qzeros)
set_weight_attrs(w2_qzeros, extra_weight_attrs)
# dont shard the w2 scales when running act order
# don't shard the w2 scales when running act order
set_weight_attrs(w2_qzeros,
{"load_full_w2": self.quant_config.desc_act})
w13_g_idx = torch.nn.Parameter(