A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 8, 11:15 UTC
[Docs] Fix typo ("defult") and double spacing (#34348)
Signed-off-by: SorenDreano <71752785+SorenDreano@users.noreply.github.com> Co-authored-by: Soren Dreano <soren@numind.ai> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
SorenDreano committed
Feb 11, 2026 at 18:02 UTC
48134a2c227541dd47b1651bfd96a70a714b0f6e
1 file changed
+1
-1
vllm/config/vllm.py
+1
-1
@@ -278,7 +278,7 @@ class VllmConfig:
278
optimization_level: OptimizationLevel = OptimizationLevel.O2
279
"""The optimization level. These levels trade startup time cost for
280
performance, with -O0 having the best startup time and -O3 having the best
281
- performance. -02 is used by defult. See OptimizationLevel for full
281
+ performance. -O2 is used by default. See OptimizationLevel for full
282
description."""
283
284
weight_transfer_config: WeightTransferConfig | None = None