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

fix some typos (#24071)

Browse Source 
Signed-off-by: co63oc <co63oc@users.noreply.github.com>
This commit is contained in:
co63oc
2025-09-03 11:44:50 +08:00
committed by GitHub
parent 136d853e65
commit 1bd007f234
32 changed files with 39 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/config/compilation.py
View File

@@ -234,7 +234,7 @@ class CompilationConfig:
- FULL_AND_PIECEWISE.
PIECEWISE mode build piecewise cudagraph only, keeping the cudagraph
incompatiable ops (i.e. some attention ops) outside the cudagraph
incompatible ops (i.e. some attention ops) outside the cudagraph
for general flexibility.
This is the default mode.

2
vllm/config/parallel.py
View File

@@ -87,7 +87,7 @@ class ParallelConfig:
data_parallel_external_lb: bool = False
"""Whether to use "external" DP LB mode. Applies only to online serving
and when data_parallel_size > 0. This is useful for a "one-pod-per-rank"
wide-EP setup in Kuberentes. Set implicitly when --data-parallel-rank
wide-EP setup in Kubernetes. Set implicitly when --data-parallel-rank
is provided explicitly to vllm serve."""
data_parallel_hybrid_lb: bool = False
"""Whether to use "hybrid" DP LB mode. Applies only to online serving