[serve.llm][bugfix] Fix the wrong device_capability issue in vllm on quantized models.#51007
Merged
kouroshHakha merged 5 commits intoray-project:masterfrom kouroshHakha:kh/fix-serve-quantizedMar 3, 2025
+32-1
Commits
Commits on Mar 1, 2025
- committed
- committed
- committed
- committed
Merge branch 'kh/fix-serve-quantized' of https://github.com/kouroshHakha/ray into kh/fix-serve-quantized
committed