Stars
FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
Huggingface-compatible SDXL Unet implementation that is readily hackable
A minimalistic educational hypervisor for Windows on AMD processors.
🏮 A hybrid Neovim configuration for productive developers who want a functional yet aesthetic Vim experience 🏮
An extremely low latency KVMFR (KVM FrameRelay) implementation for guests with VGA PCI Passthrough.
Intel® Hardware Accelerated Execution Manager (Intel® HAXM)
Hello world, with inspiration from Java enterprise backends
A collection of (mostly) technical things every software developer should know about
AlexAltea / haxm
Forked from intel/haxmIntel® Hardware Accelerated Execution Manager (Intel® HAXM)
Source code for rpcs3.net/compatibility




