informatico-madrid/blackwell-linux-infra-optimizer
Optimized vLLM deployment for NVIDIA Blackwell (RTX 5090) on Linux Kernel 6.14. Resolves SM_120 kernel incompatibilities, P2P deadlocks, and memory fragmentation for high-performance LLM inference.
High-Performance I/O Prefetch Kernel for DirectStorage, WSL2 and HFT workloads.
Optimized vLLM deployment for NVIDIA Blackwell (RTX 5090) on Linux Kernel 6.14. Resolves SM_120 kernel incompatibilities, P2P deadlocks, and memory fragmentation for high-performance LLM inference.
Techniques and numbers for estimating system's performance from first-principles
Fast, small, secure, local-first personal AI assistant infrastructure: one Rust binary for tools, memory, channels, providers, and sandboxed autonomy.
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
Rust library for OpenAI
PyTorch native quantization and sparsity for training and inference
5 captures since 2026-06-04
Cargo.toml
· rust · 4 dependencies