Popular repositories Loading

1. model-shelf model-shelf Public

   Forked from alexziskind1/model-shelf

   Model Shelf is a local-first model resolver that helps AI agents and scripts find model weights on your own storage before downloading from Hugging Face. Point it at an internal SSD, NAS, external …

   Python

2. draftbench draftbench Public

   Forked from alexziskind1/draftbench

   Benchmark tool for measuring speculative decoding speedups. Sweep draft/target model combinations and generate interactive charts.

   Python

3. llm-inference-calculator llm-inference-calculator Public

   Forked from alexziskind1/llm-inference-calculator

   TypeScript

4. llama-throughput-lab llama-throughput-lab Public

   Forked from alexziskind1/llama-throughput-lab

   Interactive launcher and benchmarking harness for llama.cpp server throughput, with tests, sweeps, and round‑robin load tools.

   Python

5. codeneedle codeneedle Public

   Forked from alexziskind1/codeneedle

   Python

6. llama-benchy llama-benchy Public

   Forked from alexziskind1/llama-benchy

   llama-benchy - llama-bench style benchmarking tool for all backends

   Python