Loading...
Loading...
Found 21 Skills
Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute.
MLA (Multi-Latent Attention) cost models, regime analysis, and kernel selection guide. Use when: (1) reasoning about which kernel approach to use for a given regime, (2) understanding cost model tradeoffs between FlashMLA, FlashAttention, and MLAvar6+, (3) analyzing roofline behavior across decode/speculative/prefill regimes, (4) setting optimization targets, (5) understanding MLA math and absorption trick.
Delegate menial, well-scoped coding tasks to a cheap Qwen-backed subagent via the `claude-9arm` command instead of burning Claude tokens/quota. Use when the work is mechanical and low-risk — bulk renames, formatting, boilerplate, find-replace, grep-style search & summarization, reading/condensing logs or files, test/docstring/comment scaffolding, or running builds/linters/tests and reporting pass-fail. Also use when the user says "use qwen", "delegate this", "send it to 9arm/qwen", or "do this cheaply". Do NOT use for architecture, design, debugging judgment, security-sensitive edits, or anything needing this conversation's context.
ESM2 protein language model for embeddings and sequence scoring. Use this skill when: (1) Computing pseudo-log-likelihood (PLL) scores, (2) Getting protein embeddings for clustering, (3) Filtering designs by sequence plausibility, (4) Zero-shot variant effect prediction, (5) Analyzing sequence-function relationships. For structure prediction, use chai or boltz. For QC thresholds, use protein-qc.
Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3, Qwen3, Qwen3-Next, and VLM bring-up work.
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.
SOTA Computer Vision Expert (2026). Specialized in YOLO26, Segment Anything 3 (SAM 3), Vision Language Models, and real-time spatial analysis.
Guidelines for deep learning development with PyTorch, Transformers, Diffusers, and Gradio for LLM and diffusion model work.
Understanding Reinforcement Learning from Human Feedback (RLHF) for aligning language models. Use when learning about preference data, reward modeling, policy optimization, or direct alignment algorithms like DPO.