MadeBy561/MadeBy561
Lifelong developer. Local Inference Lab contributor, maker of Doorplate.
Lifelong developer. Proud contributor to Local Inference Lab, a non-profit building open tooling for running LLMs on NVIDIA Blackwell. Creator of Doorplate.
Repositories
MadeBy561/llm-inference-bench
LLM inference decode throughput benchmark with Rich TUI dashboard. Measures token generation speed across concurrency levels and context lengths. Supports SGLang and vLLM engines.
MadeBy561/blackwell-llm-docker
Docker images for LLM inference (SGLang + vLLM) on NVIDIA Blackwell GPUs (SM120, CUDA 13.2)
MadeBy561/reap-bench
Run NVIDIA's GLM-5.2 eval axes (GPQA Diamond, SciCode, ...) against any OpenAI-compatible endpoint — measure what a REAP prune/quant costs.
MadeBy561/b12x
MadeBy561/sm120-dspark-cookbook
MadeBy561/sm120-sa-mtp-hybird
MadeBy561/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs