amd-agi/hyperloom

amd-agi/hyperloom · .claude/skills/analyze-upstream-pr/SKILL.md · Analyze whether an upstream pull request applies to an AMD/ROCm deployment. Invoke with the PR's repository and number…

amd-agi/hyperloom · .claude/skills/check-prior-art/SKILL.md · Check whether a planned optimization already exists upstream before building it. Invoke with a one-sentence mechanism…

amd-agi/hyperloom · .claude/skills/review-pr/SKILL.md · Review a Hyperloom pull request. Invoke with a PR number whenever asked to review, re-review or sanity-check a PR in…

amd-agi/hyperloom · AGENTS.md

amd-agi/hyperloom · CLAUDE.md

amd-agi/hyperloom · docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b/SKILL.md · Run a 4-hour multi-node Hyperloom Qwen3-30B-A3B optimization (Infera PD-disaggregated or RayJob aggregated) with…

amd-agi/hyperloom · examples/hyperloom-custom-advanced/SKILL.md · Run an advanced configurable Hyperloom optimization session with explicit model, framework, workload, objective, and…

amd-agi/hyperloom · examples/hyperloom-qwen3-14b-fp8-12h-forge/SKILL.md · Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session on SGLang, vLLM or ATOM with the per-kernel KernelForge…

amd-agi/hyperloom · examples/hyperloom-qwen3-14b-fp8-12h/SKILL.md · Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session on SGLang, vLLM or ATOM. Use when the user wants a…

amd-agi/hyperloom · examples/hyperloom-qwen3-8b-3h/SKILL.md · Run a 3-hour Hyperloom Qwen3-8B FRAMEWORK_AGENT (OPTIMIZE) session without the Kernel Agent. Use when the user wants a…

amd-agi/hyperloom · examples/skills/hyperloom-workload-optimizer/SKILL.md · Autonomously optimizes end-to-end LLM inference throughput on AMD Instinct GPUs and reports a validated gain, using the…

amd-agi/hyperloom · src/hyperloom/agents/critic/SKILL.md · Critic layer for the inference optimizer. Use when Conductor asks for a Critic Review verdict on Orchestration or…

amd-agi/hyperloom · src/hyperloom/agents/quantization/SKILL.md · Hyperloom sub-agent that drives the AMD Quark PTQ skill chain end-to-end from a natural-language prompt. Produces a…

amd-agi/hyperloom · src/hyperloom/inference_optimizer/SKILL.md · Launches and monitors Hyperloom's multi-agent inference optimizer for LLM serving on AMD GPUs. Use when the user asks…

amd-agi/hyperloom · src/hyperloom/inference_optimizer/breakdown/SKILL.md · Build a single self-contained `session_breakdown.json` capturing every fact a dashboard needs about one hyperloom…

amd-agi/hyperloom · src/hyperloom/inference_optimizer/multi_node/SKILL.md · Multi-node companion to the inference_optimizer skill. Use when the user prompt asks for inference optimization that…

amd-agi/hyperloom · src/hyperloom/skills/hyperloom-setup/SKILL.md · Configures Hyperloom after pip install --target . by collecting core LLM/runtime settings once, choosing direct…

amd-agi/hyperloom · src/hyperloom_arbor/.claude/skills/campaign-archive/SKILL.md · Archive a running Arbor campaign to git and rebuild any campaign's exact source tree from the archive. Use when syncing…

amd-agi/hyperloom · src/hyperloom_arbor/.claude/skills/dashboard/SKILL.md · Watch Arbor campaigns in a browser. Local mode shows one campaign live, collected over ssh where its agents run; global…

amd-agi/hyperloom · src/hyperloom_arbor/.claude/skills/dossier/SKILL.md · Find, or write if it is missing, the dossier an optimization campaign starts from, for one model, workload and GPU…

amd-agi/hyperloom · src/hyperloom_arbor/.claude/skills/geko-hipblaslt-tuning/SKILL.md · Set up and run geko hipBLASLt GEMM tuning for DeepSeek-V4.1-Flash + vLLM/AgentX serving on AMD gfx950 (MI355X), then…

amd-agi/hyperloom · src/hyperloom_arbor/.claude/skills/hardware/SKILL.md · AMD Instinct hardware facts for kernel authoring, rooflines and communication — MI350X/MI355X (gfx950, CDNA4) and…

amd-agi/hyperloom · src/hyperloom_arbor/.claude/skills/kernels/SKILL.md · Before writing, porting or tuning a GPU kernel for LLM serving on AMD Instinct (MI350X/MI355X gfx950, MI300X gfx942) —…

amd-agi/hyperloom · src/hyperloom_arbor/.claude/skills/knowledge-collector/SKILL.md · Share what an Arbor campaign learned so the next campaign on the model starts from it, and read what earlier campaigns…

amd-agi/hyperloom · src/hyperloom_arbor/.claude/skills/merge-optimization-trees/SKILL.md · Merge several independently-discovered optimizations (PRs, campaign trees, forks) into one measurable baseline: branch…

amd-agi/hyperloom · src/hyperloom_arbor/.claude/skills/plan/SKILL.md · Write the plan for an optimization round before the round runs, from the dossier, the ledger and the outcomes of…

amd-agi/hyperloom · src/hyperloom_arbor/.claude/skills/profiler/SKILL.md · Profile an LLM serving workload on ROCm to find where GPU time goes, with TraceLens on PyTorch-profiler traces of the…

amd-agi/hyperloom · src/hyperloom_arbor/.claude/skills/realtime-collector/SKILL.md · Push an Arbor campaign's live state (phase, iteration in flight, verdicts, baseline and best, the log's tail) to the…

amd-agi/hyperloom · src/hyperloom_arbor/.claude/skills/serving-playbook/SKILL.md · The rules that hold for serving changes on AMD GPUs (price on this node, prove each arm differed, judge a policy at…

amd-agi/hyperloom · src/hyperloom_kb/skills/hyperloom-kb/SKILL.md · Operates an Experience KB service with the hyperloom-kb CLI. Checks its health, labels its state, restores a label to…

amd-agi/hyperloom · src/kernelforge/knowledge/local_wiki/resources/languages/flydsl/skills/profile/kernel-trace-analysis/SKILL.md · Profile GPU kernels using rocprofv3 to collect ATT instruction-level traces, then analyze the trace data using…