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

[Doc]: fix typos in Python scripts (#23828)

Browse Source 
Signed-off-by: Didier Durand <durand.didier@gmail.com>
This commit is contained in:
Didier Durand
2025-08-28 14:37:38 +02:00
committed by GitHub
parent bfab219648
commit d3da2eea54
10 changed files with 12 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py
View File

@@ -579,7 +579,7 @@ class CompressedTensorsConfig(QuantizationConfig):
format = scheme_dict.get("format")
# Find the sparsity scheme of the layer
# assume that fused layers inerhit first component's sparsity scheme
# assume that fused layers inherit first component's sparsity scheme
sparsity_targets = (self.sparsity_scheme_map.keys() -
set(self.sparsity_ignore_list))
sparsity_scheme: Optional[SparsityCompressionConfig] = None

2
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py
View File

@@ -71,7 +71,7 @@ class CompressedTensorsMoEMethod(FusedMoEMethodBase):
) -> "CompressedTensorsMoEMethod":
# TODO: @dsikka: refactor this to use schemes as other kernels
# are supported + check if the layer is being ignored.
# Check if a using "Linear" to select scheems
# Check if a using "Linear" to select schemes
if "Linear" in quant_config.target_scheme_map:
matched_target = "Linear"
else: