GitHub Release Tracker

08/21

8

NVIDIA/NVIDIA GPU Operator v26.7.0

Automates installation and lifecycle management of GPU drivers, container runtimes, and monitoring on Kubernetes nodes.

Go 2847☆ 2735d old #golang #kubernetes #go #gpu #cuda

08/20

6

raketenkater/ggrun v3.2.8

Auto-tuned launcher that measures multi-GPU hardware for GGUF models, picks an optimal llama.cpp/ik_llama.cpp backend, and serves an OpenAI-compatible API.

Go 267☆ 169d old #golang #llm #go #llama-cpp #cuda

08/17

6

raketenkater/ggrun v3.2.7

Auto-tuned launcher that measures multi-GPU hardware for GGUF models, picks an optimal llama.cpp/ik_llama.cpp backend, and serves an OpenAI-compatible API.

Go 267☆ 169d old #golang #llm #go #llama-cpp #cuda

08/23

5

sonots/Cumo v0.5.10

CUDA-aware GPU-optimized numerical library compatible with Ruby Numo for enhanced performance.

C 99☆ 3208d old #ruby #c #cuda #numo #scicentific-computing

08/20

5

sonots/Cumo v0.5.9

CUDA-aware GPU-optimized numerical library compatible with Ruby Numo for enhanced performance.

C 99☆ 3208d old #ruby #c #cuda #numo #scicentific-computing

08/17

5

sonots/Cumo v0.5.8

CUDA-aware GPU-optimized numerical library compatible with Ruby Numo for enhanced performance.

C 99☆ 3208d old #ruby #c #cuda #numo #scicentific-computing

08/17

3

Avarok-Cybersecurity/Atlas Inference Engine b236

Pure Rust LLM inference engine focused on fast, hardware-optimized local model execution across GPUs and CPUs.

JavaScript 650☆ 104d old #javascript #cuda #llm-inference #gb10 #mamba

08/17

3

Avarok-Cybersecurity/Atlas Inference Engine b234

Pure Rust LLM inference engine focused on fast, hardware-optimized local model execution across GPUs and CPUs.

JavaScript 650☆ 104d old #javascript #cuda #llm-inference #gb10 #mamba

08/16

3

Avarok-Cybersecurity/Atlas Inference Engine b233

Pure Rust LLM inference engine focused on fast, hardware-optimized local model execution across GPUs and CPUs.

JavaScript 650☆ 104d old #javascript #cuda #llm-inference #gb10 #mamba

08/16

3

Avarok-Cybersecurity/Atlas Inference Engine b232

Pure Rust LLM inference engine focused on fast, hardware-optimized local model execution across GPUs and CPUs.

JavaScript 650☆ 104d old #javascript #cuda #llm-inference #gb10 #mamba

08/16

3

Avarok-Cybersecurity/Atlas Inference Engine b231

Pure Rust LLM inference engine focused on fast, hardware-optimized local model execution across GPUs and CPUs.

JavaScript 650☆ 104d old #javascript #cuda #llm-inference #gb10 #mamba

08/16

3

beam-cloud/Beta9 gateway-0.1.757

Fast serverless runtime for GPU inference, isolated sandboxes, and scalable background jobs.

Go 1744☆ 1006d old #golang #generative-ai #go #gpu #cuda

08/16

3

Avarok-Cybersecurity/Atlas Inference Engine b230

Pure Rust LLM inference engine focused on fast, hardware-optimized local model execution across GPUs and CPUs.

JavaScript 650☆ 104d old #javascript #cuda #llm-inference #gb10 #mamba

08/21	8	NVIDIA/NVIDIA GPU Operator v26.7.0 Automates installation and lifecycle management of GPU drivers, container runtimes, and monitoring on Kubernetes nodes. Go 2847☆ 2735d old #golang #kubernetes #go #gpu #cuda
08/20	6	raketenkater/ggrun v3.2.8 Auto-tuned launcher that measures multi-GPU hardware for GGUF models, picks an optimal llama.cpp/ik_llama.cpp backend, and serves an OpenAI-compatible API. Go 267☆ 169d old #golang #llm #go #llama-cpp #cuda
08/17	6	raketenkater/ggrun v3.2.7 Auto-tuned launcher that measures multi-GPU hardware for GGUF models, picks an optimal llama.cpp/ik_llama.cpp backend, and serves an OpenAI-compatible API. Go 267☆ 169d old #golang #llm #go #llama-cpp #cuda
08/23	5	sonots/Cumo v0.5.10 CUDA-aware GPU-optimized numerical library compatible with Ruby Numo for enhanced performance. C 99☆ 3208d old #ruby #c #cuda #numo #scicentific-computing
08/20	5	sonots/Cumo v0.5.9 CUDA-aware GPU-optimized numerical library compatible with Ruby Numo for enhanced performance. C 99☆ 3208d old #ruby #c #cuda #numo #scicentific-computing
08/17	5	sonots/Cumo v0.5.8 CUDA-aware GPU-optimized numerical library compatible with Ruby Numo for enhanced performance. C 99☆ 3208d old #ruby #c #cuda #numo #scicentific-computing
08/17	3	Avarok-Cybersecurity/Atlas Inference Engine b236 Pure Rust LLM inference engine focused on fast, hardware-optimized local model execution across GPUs and CPUs. JavaScript 650☆ 104d old #javascript #cuda #llm-inference #gb10 #mamba
08/17	3	Avarok-Cybersecurity/Atlas Inference Engine b234 Pure Rust LLM inference engine focused on fast, hardware-optimized local model execution across GPUs and CPUs. JavaScript 650☆ 104d old #javascript #cuda #llm-inference #gb10 #mamba
08/16	3	Avarok-Cybersecurity/Atlas Inference Engine b233 Pure Rust LLM inference engine focused on fast, hardware-optimized local model execution across GPUs and CPUs. JavaScript 650☆ 104d old #javascript #cuda #llm-inference #gb10 #mamba
08/16	3	Avarok-Cybersecurity/Atlas Inference Engine b232 Pure Rust LLM inference engine focused on fast, hardware-optimized local model execution across GPUs and CPUs. JavaScript 650☆ 104d old #javascript #cuda #llm-inference #gb10 #mamba
08/16	3	Avarok-Cybersecurity/Atlas Inference Engine b231 Pure Rust LLM inference engine focused on fast, hardware-optimized local model execution across GPUs and CPUs. JavaScript 650☆ 104d old #javascript #cuda #llm-inference #gb10 #mamba
08/16	3	beam-cloud/Beta9 gateway-0.1.757 Fast serverless runtime for GPU inference, isolated sandboxes, and scalable background jobs. Go 1744☆ 1006d old #golang #generative-ai #go #gpu #cuda
08/16	3	Avarok-Cybersecurity/Atlas Inference Engine b230 Pure Rust LLM inference engine focused on fast, hardware-optimized local model execution across GPUs and CPUs. JavaScript 650☆ 104d old #javascript #cuda #llm-inference #gb10 #mamba