@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 61af633256
Fork 0

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 16, 03:15 UTC

[BUGFIX] Fix `UnspecifiedPlatform` package name (#11916)

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

Kunshang Ji committed Jan 10, 2025 at 16:20 UTC 61af6332565d0093855fee7266699e548b1c0d1c
1 file changed +1 -1
vllm/platforms/__init__.py
+1 -1
@@ -179,7 +179,7 @@ def resolve_current_platform_cls_qualname() -> str:
179 logger.info("Automatically detected platform %s.",
180 activated_builtin_plugins[0])
181 else:
182 - platform_cls_qualname = "vllm.interface.UnspecifiedPlatform"
182 + platform_cls_qualname = "vllm.platforms.interface.UnspecifiedPlatform"
183 logger.info(
184 "No platform detected, vLLM is running on UnspecifiedPlatform")
185 return platform_cls_qualname