← all publishers

AMD-AGI

@amd-agi source repo

Report this profile Claim this profile

• 14 skills
• 0 followers
• 13 hours ago last updated

1. ▌
   Critic Agent · amd-agi bundle

   Critic layer for the inference optimizer. Use when Conductor asks for a Critic Review verdict on Orchestration or Kernel proposals, conversation-driven decision review, KB recall/ingest guidance, cross-run synthesis, or Devil's advocate review signals.
   0
   installs
2. ▌
   Hyperloom Qwen3 8b 3h · amd-agi

   Run a 3-hour Hyperloom Qwen3-8B FRAMEWORK_AGENT (OPTIMIZE) session without the Kernel Agent. Use when the user wants a short, framework-only Hyperloom demo on the local AMD ROCm environment.
   0
   installs
3. ▌
   Framework · amd-agi bundle

   Framework Agent — Sibling Skill
   0
   installs
4. ▌
   Robustness Agent · amd-agi bundle

   Independent guardian daemon for Hyperloom inference optimization. Implements the inference_optimizer "robustness" reactor so the Coordinator can call it as a Backend, plus a standalone loop for dev. Owns continuous health monitoring, RCA, and scheduling-police capabilities (prune_branch / delegate).
   0
   installs
5. ▌
   Quantization Agent · amd-agi bundle

   Hyperloom sub-agent that drives the AMD Quark PTQ skill chain end-to-end from a natural-language prompt. Produces a HuggingFace-format quantized model directory plus a structured assessment of every artifact that the Quark workflow + validator + llm-eval skills emit. Single public entry: `quantize_via_prompt(prompt, *, workspace, quark_root=None, interactive=None, acceptable_eval_gap=None, max_requantize_attempts=1)`.
   0
   installs
6. ▌
   Inference Optimizer · amd-agi bundle

   Launches and monitors Hyperloom's multi-agent inference optimizer for LLM serving on AMD GPUs. Use when the user asks to optimize an inference model, run Magpie benchmarks/profiles, resume an inference_optimizer session, tune SGLang/vLLM serving parameters, run TraceLens/kernel-agent, or validate end-to-end throughput gains in a new inference environment.
   0
   installs
7. ▌
   Hyperloom Custom Advanced · amd-agi

   Run an advanced configurable Hyperloom optimization session with explicit model, framework, workload, objective, and phase toggles. Use when the user wants more control than the fixed 3h or 12h demo presets.
   0
   installs
8. ▌
   Hyperloom Qwen3 14b Fp8 12h · amd-agi

   Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session. Use when the user wants a medium-length Hyperloom demo on the local AMD ROCm environment.
   0
   installs
9. ▌
   Hyperloom Setup · amd-agi

   Configure Hyperloom in the current agent workspace after pip install --target . by collecting LLM settings, choosing a bare-metal or Docker run mode, writing .env, and running the setup backend on baremetal hosts only.
   0
   installs
10. ▌
    Hyperloom Qwen3 14b Fp8 12h Forge · amd-agi

    Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session with the per-kernel KernelForge backend instead of GEAK. Use when the user wants the medium-length Hyperloom demo and has asked for the forge kernel backend.
    0
    installs
11. ▌
    Session Breakdown · amd-agi bundle

    Build a single self-contained `session_breakdown.json` capturing every fact a dashboard needs about one hyperloom optimization session. Use when the user mentions session-breakdown, kernel attribution, a stats/reporting service, capability summary, or wants to surface hyperloom data to an external consumer (a results/stats service, notebook, dashboard).
    0
    installs
12. ▌
    Hyperloom Inference Optimizer Multi Node · amd-agi bundle

    Multi-node companion to the inference_optimizer skill. Use when the user prompt asks for inference optimization that needs more GPU / memory than a single pod provides (i.e. ``nodes >= 2``) — typical prompt signals are ``Nodes=N`` / ``N pods`` / ``TP=N`` larger than one pod's GPU count, or any model that cannot fit on one pod's GPUs. Drives a platform-provisioned multi-node cluster through the ``hyperloom.inference_optimizer.multi_node`` Python CLI.
    0
    installs
13. ▌
    Hyperloom Remote Mn Qwen3 30b · amd-agi

    Run a 4-hour multi-node Hyperloom Qwen3-30B-A3B optimization (Infera PD-disaggregated or RayJob aggregated) with --nodes 2 and sglang MoE tuning on MI325X. Hand this skill to the agent to launch and monitor the run.
    0
    installs
14. ▌
    Kernel Trace Analysis · amd-agi bundle

    Profile GPU kernels using rocprofv3 to collect ATT instruction-level traces, then analyze the trace data using hotspot_analyzer.py to identify top-K stall hotspots (VMEM-load, VMEM-wait, LDS/SMEM-wait, barrier, MFMA stalls) mapped back to source lines, and produce an actionable optimization plan. Usage: /kernel-trace-analysis <cmd> Can also analyze an existing dispatch dir directly: /kernel-trace-analysis --dir <path>
    0
    installs