| Index | index by Group | index by Distribution | index by Vendor | index by creation date | index by Name | Mirrors | Help |
The search service can find package by either name (apache), provides(webserver), absolute file names (/usr/bin/apache), binaries (gprof) or shared libraries (libXm.so.2) in standard path. It does not support multiple arguments yet...
The System and Arch are optional added filters, for example System could be "redhat", "redhat-7.2", "mandrake" or "gnome", Arch could be "i386" or "src", etc. depending on your system.
vLLM is a fast and easy-to-use library for LLM inference and serving. This build includes vLLM's optimised C++ CPU kernels (VLLM_TARGET_DEVICE=cpu), backed by a statically linked oneDNN -- and, on aarch64, the Arm Compute Library. The CUDA/GPU kernels, the audio/video (torchaudio/torchcodec/ torchvision) helpers and the optional Rust-accelerated tool parser are not included. It conflicts with the plain python-vllm package; install one or the other.
| Package | Summary | Distribution | Download |
| python313-vllm-cpu-0.26.0-7.1.riscv64.html | A high-throughput and memory-efficient inference and serving engine for LLMs | OpenSuSE Ports Tumbleweed for riscv64 | python313-vllm-cpu-0.26.0-7.1.riscv64.rpm |
| python313-vllm-cpu-0.26.0-2.1.x86_64.html | A high-throughput and memory-efficient inference and serving engine for LLMs | OpenSuSE Tumbleweed for x86_64 | python313-vllm-cpu-0.26.0-2.1.x86_64.rpm |
Generated by rpm2html 1.6