burtenshaw

Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.

Use Hermes delegate_task cleanly in this repo for planner, reviewer, researcher, reporter, experiment-worker, and memory-keeper roles.

Run one Autolab benchmark experiment safely on Hugging Face Jobs. Use when a planner, reviewer, or experiment worker is preparing, auditing, launching, or reviewing a single train.py hypothesis against the current local promoted master.

Operate the local Trackio reporter for Autolab HF Jobs. Use when a reporter or planner needs to inspect scores, active jobs, worker anomalies, duplicate launches, or the overall experiment board.

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing repositories, models, datasets, and Spaces on the Hugging Face Hub. Replaces now deprecated `huggingface-cli` command.

Orchestrate Docker-isolated, branch-based multi-agent git workflows with normies. Use for parallel edits, retries, and explicit review/integration gates.

Orchestrate Docker-isolated, branch-based multi-agent git workflows with normies. Use for parallel edits, batched tasks, retries, and explicit review/integration gates. Prefer this over ad-hoc shell loops for multi-step coordination; skip for trivial one-file edits that do not need orchestration.

Provides guidance for writing and benchmarking optimized CUDA kernels for NVIDIA GPUs (H100, A100, T4) targeting HuggingFace diffusers and transformers libraries. Supports models like LTX-Video, Stable Diffusion, LLaMA, Mistral, Qwen, and Qwen3. Includes integration with HuggingFace Kernels Hub (get_kernel) for loading pre-compiled kernels. Includes benchmarking scripts to compare kernel performance against baseline implementations.

Run OpenEnv scaling and concurrency benchmark experiments. Use when deploying benchmark infrastructure (local uvicorn, local docker, HF Spaces, SLURM single-node, SLURM multi-node), running test_scaling.py tests, or analyzing experiment results. Triggers on requests to benchmark, test scaling, measure concurrency, compare HTTP vs WebSocket performance, or review experiment reports.