Categories / More categories

LLM Infrastructure

Running and serving large language models, LLM API gateways and proxies, and retrieval-augmented generation (RAG) systems.

Repos

123

Stars

73,530

Last 30 days

+5,266

RustingStudio

Pure-Rust inference engine for Qwen GGUF models (Qwen3 to Qwen3.8, dense and MoE up to 770B+). CUDA and Vulkan (NVIDIA, AMD), hybrid CPU+GPU experts, MTP speculative decoding, OpenAI and Anthropic compatible server. Up to ~1.7x llama.cpp decode on a 12 GB RTX 3060.

Created Oct 2026

anthropic-api cuda gguf inference llama-cpp
Total297
30 days +291
giannisanni

SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs. Zero-config multi-GPU: measures PCIe bandwidth, places attention and hot experts where they fit.

Created Jul 2026

Total239
30 days +9
ferrumox

A local LLM server built for concurrent work. Drop-in replacement for Ollama and/or OpenAI and Ollama APIs on one port. Requests that share a prompt reuse each other's KV cache instead of each prefilling it. Rust, wrapping llama.cpp.

Created Mar 2026

Total191
30 days +2
truespar

Native Rust inference server for open models on NVIDIA and Apple Silicon. OpenAI- and Anthropic-compatible APIs, GGUF + safetensors + MLX, FP8/NVFP4/MXFP4/Q8/Q4, built-in Studio

Created Sep 2026

ai aimodels blackwell cuda inference
Total165
30 days +28
midagedev

Hybrid GPU + CPU inference for mixture-of-experts models, written in Rust down to the CUDA kernels. A drop-in llama-server.

Created Sep 2026

Total78
30 days +0
gpillon

An inference engine for NVIDIA RTX card card family, built for a coding agent and its subagents, and a companion that listens, reads and draws: Qwen3.8 27B and 125B Flash-Next MoE, Qwen-Image-2.1, Qwen3-ASR on the CPU. OpenAI-compatible API and Playground in one binary.

Created Sep 2026

ada ampere blackwell coding-agents cuda
Total68
30 days +0
pegainfer-project

OpenAI-compatible speech serving in Rust: streaming TTS and full-duplex voice over GPT-Live. 128 concurrent PersonaPlex sessions on one GPU.

Created Sep 2026

cuda full-duplex gpt-live inference-server llm-serving
Total51
30 days +0