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

[Doc]: fixing multiple typos in diverse files (#33256)

Browse Source 
Signed-off-by: Didier Durand <durand.didier@gmail.com>
Signed-off-by: Didier Durand <2927957+didier-durand@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Didier Durand
2026-01-29 09:52:03 +01:00
committed by GitHub
parent abb34ac43a
commit 31b25f6516
14 changed files with 20 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/fused_moe/shared_fused_moe.py
View File

@@ -30,7 +30,7 @@ class SharedFusedMoE(FusedMoE):
# Disable shared expert overlap if:
# - we are using eplb with non-default backend, because of correctness issues
# - we are using flashinfer with DP, since there nothint to gain
# - we are using flashinfer with DP, since there nothing to gain
# - we are using marlin kernels
backend = self.moe_parallel_config.all2all_backend
self.use_overlapped = (

2
vllm/model_executor/layers/quantization/kernels/scaled_mm/ScaledMMLinearKernel.py
View File

@@ -22,7 +22,7 @@ class ScaledMMLinearLayerConfig:
@dataclass
class Int8ScaledMMLinearLayerConfig(ScaledMMLinearLayerConfig):
# TODO: Chnage to QuantKey like FP8ScaledMMLinearLayerConfig
# TODO: Change to QuantKey like FP8ScaledMMLinearLayerConfig
is_static_input_scheme: bool
is_channelwise: bool
input_symmetric: bool

2
vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py
View File

@@ -119,7 +119,7 @@ def choose_scaled_mm_linear_kernel(
config (_KernelConfigT): Description of the linear layer
to be implemented.
possible_kernels (dict[PlatformEnum, list[_KernelT]]): A
dictionary of platforms and their list list of possible kernels.
dictionary of platforms and their list of possible kernels.
compute_capability (Optional[int], optional): The compute capability of
the target device, if None uses `current_platform` to get the
compute capability. Defaults to None.