TensorRails/warmctl

Local-first engineering agent that deploys, benchmarks and tunes vLLM/SGLang inference services on your own GPUs, with auditable run evidence.

Run multiple resource-heavy Large Models (LM) on the same machine with limited amount of VRAM/other resources by exposing them on different ports and loading/unloading them on demand

Self-hosted vLLM inference for Qwen3.6-35B-A3B-NVFP4

Check whether your GPU can run an Ollama model. Estimates VRAM, KV cache, tokens/sec and power for single and multi-GPU setups.

A tool for benchmarking LLMs on Modal

NPU Ollama - An Ollama/OpenAI compatible API for Intel OpenVINO compatible computers

A high-throughput and memory-efficient inference and serving engine for LLMs

Evidence-driven SGLang inference deployment optimization.

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.