amazon-science/ammo / ai_cli_session/.codex/skills/ammo
ammo
UnverifiedProfile and optimize GPU kernels for vLLM inference on NVIDIA GPUs. Use when targeting a specific model, hardware, dtype, parallelism, and workload to improve latency.
eval/causal/tests/fixtures/sample_snapshot.json
View on GitHub{
"parsed_at": "2026-03-20T00:00:00+00:00",
"artifact_dir": "/workspace/vllm/kernel_opt_artifacts/test",
"target": {
"model_id": "test-model",
"hardware": "L40S",
"dtype": "fp8",
"tp": 1
},
"environment": {
"gpu_model": "NVIDIA L40S",
"cuda_version": "12.9"
},
"campaign": {
"status": "campaign_exhausted",
"total_rounds": 1,
"cumulative_speedup_vs_round1": 1.05,
"shipped_optimizations_count": 1,
"shipped_optimization_ids": ["op001"],
"rounds": [
{
"round_id": 1,
"top_bottleneck_share_pct": 29.8,
"candidates_proposed": 2,
"candidates_selected": 2,
"candidates_shipped": 1,
"candidates_failed": 1,
"round_e2e_speedup": 1.05,
"cumulative_speedup_after": 1.05
}
]
},
"gates": {
"phase1_baseline": {
"status": "PASS"
},
"validation_gates": [
{
"track_id": "op001",
"status": "PASSED",
"correctness": true,
"kernel_speedup": 1.15,
"e2e_speedup": 1.05
},
{
"track_id": "op002",
"status": "FAILED",
"correctness": false,
"kernel_speedup": null,
"e2e_speedup": null
},
{
"track_id": "op003",
"status": "GATED_PASS",
"correctness": true,
"kernel_speedup": 1.08,
"e2e_speedup": 1.03,
"per_bs_verdict": {
"1": "PASS",
"8": "PASS",
"32": "REGRESSED"
}
}
],
"integration": {
"status": "single_pass",
"final_decision": "ship_op001"
}
},
"debate": {
"campaign_rounds_with_debate": 1,
"total_proposals": 2,
"proposals_with_micro_experiments": 1,
"proposals_with_grounded_data": 2,
"micro_experiment_rate": 0.5,
"grounding_rate": 1.0,
"total_debate_rounds_across_campaign": 2,
"all_candidate_scores": [7.5, 5.2],
"per_campaign_round": [
{
"campaign_round": 1,
"proposals_count": 2,
"debate_rounds": 2
}
]
},
"tracks": [
{
"op_id": "op001",
"campaign_round": 1,
"status": "PASSED",
"correctness": true,
"kernel_speedup": 1.15,
"e2e_speedup": 1.05
},
{
"op_id": "op002",
"campaign_round": 1,
"status": "FAILED",
"correctness": false,
"kernel_speedup": null,
"e2e_speedup": null
},
{
"op_id": "op003",
"campaign_round": 1,
"status": "GATED_PASS",
"correctness": true,
"kernel_speedup": 1.08,
"e2e_speedup": 1.03
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |