- Munich, Germany
Stars
Incremental rust builds up to 92x faster than cargo/rustc. Backed by Y Combinator (F26).
Offline NVIDIA Blackwell VBIOS editor.
Load a modified VBIOS per NVIDIA GPU at boot on Linux, in memory, through the open kernel modules
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per re…
A very-low-resource API-compatible replacement for Ray
GLM-5.3-Flash (NVFP4) at TP=4 across 4x ASUS GX10 / GB10 - vLLM + mentat instead of Ray, 524k context, DFlash2. Minimal working recipe.
Run GLM-5.3 (744B), DeepSeek-V4.1-Flash (748B), MiniMax-M3.1-Flash (428B), GLM-5.3-Flash (321B) and Hy4-Flash (220B) on your own GPUs - from 8 GB of VRAM, NVIDIA and AMD, one dashboard, OpenAI- and…
Reverse engineer anything with agents, from app behavior down to native binaries.
NVIDIA's CUDA platform for Rust. Host runtime crates plus Tile (cutile-rs) and SIMT (cuda-oxide) kernel programming models in idiomatic Rust.
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
High-performance single-GPU inference for selected model checkpoints and GPUs.
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
LLM Inference Engine for Metal, CUDA and Vulkan.
openvi-foundation / openvue
Forked from primefaces/primevueMIT-licensed fork of PrimeVue. 80+ Vue 3 UI components, Nuxt support and one-command migration.
MiMo-V2.6-Pro-RL on 8 x DGX Spark
Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.
Low-latency collective transport and distributed LLM serving stack for switchless GB10 clusters.
"O(log N) MoE Expert routing via RT Core ray tracing. BVH traversal replaces matrix multiplication in neural language models."
Educational reference: NVIDIA Blackwell SM100 vs SM120, NVFP4, tcgen05, MoE inference on consumer Blackwell
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
A hierarchical inference engine for frontier MoE models: hot experts on the GPU (CUDA, Vulkan), warm ones in RAM, cold ones streamed from NVMe. Written in C, runs on the hardware you already own.
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
Agent skills synthesizing years of software engineering discipline into a prescriptive methodology for solo developers
Rust client for the huggingface hub aiming for minimal subset of features over `huggingface-hub` python package
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
AI inference, packed simply. A blazing-fast, zero-dependency WebGPU runtime to run GGUF models directly in the browser. Features a symmetric API for seamless local execution and cloud provider rout…
Tile primitives for speedy kernels
aidendle94 / vllm
Forked from vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMs