Skip to content

amazon-science/ammo / ai_cli_session/.codex/skills/ammo

Profile and optimize GPU kernels for vLLM inference on NVIDIA GPUs. Use when targeting a specific model, hardware, dtype, parallelism, and workload to improve latency.

FileKindSize
RUNTIME.mdmarkdown4.9 KB
SKILL.mdskill md18.5 KB
agents/ammo-auditor.mdmarkdown9.1 KB
agents/ammo-champion.mdmarkdown9.6 KB
agents/ammo-delegate.mdmarkdown3.2 KB
agents/ammo-implementer.mdmarkdown13.8 KB
agents/ammo-investigator.mdmarkdown4.0 KB
agents/ammo-report.mdmarkdown2.9 KB
agents/ammo-researcher.mdmarkdown10.3 KB
agents/ammo-resolver.mdmarkdown4.4 KB
agents/ammo-transcript-monitor.mdmarkdown7.8 KB
agents/openai.yamlexecutablescript313 B
data/ATTRIBUTION.mdmarkdown1.4 KB
data/gsm8k_full.jsonexecutablescript735.5 KB
data/gsm8k_subset.jsonexecutablescript116.8 KB
eval/EVAL-SKILL.mdexecutablescript21.8 KB
eval/agents/transcript_grader.mdexecutablescript18.0 KB
eval/causal/__init__.pyexecutablescript137 B
eval/causal/agents/causal_analyzer.mdexecutablescript10.5 KB
eval/causal/build_dag.pyexecutablescript21.6 KB
eval/causal/diff_versions.pyexecutablescript38.5 KB
eval/causal/extract_events.pyexecutablescript36.3 KB
eval/causal/generate_postmortem.pyexecutablescript17.0 KB
eval/causal/score_nodes.pyexecutablescript21.5 KB
eval/causal/templates/narrative_template.mdexecutablescript472 B
eval/causal/templates/viz_template.htmlexecutablescript9.5 KB
eval/causal/tests/__init__.pyexecutablescript151 B
eval/causal/tests/conftest.pyexecutablescript448 B
eval/causal/tests/fixtures/sample_session.jsonlexecutablescript10.4 KB
eval/causal/tests/fixtures/sample_session_data.jsonexecutablescript3.4 KB
eval/causal/tests/fixtures/sample_snapshot.jsonexecutablescript2.5 KB
eval/causal/tests/test_build_dag.pyexecutablescript2.7 KB
eval/causal/tests/test_diff_versions.pyexecutablescript13.5 KB
eval/causal/tests/test_extract_events.pyexecutablescript3.7 KB
eval/causal/tests/test_generate_postmortem.pyexecutablescript3.1 KB
eval/causal/tests/test_score_nodes.pyexecutablescript3.3 KB
eval/scripts/aggregate_versions.pyexecutablescript15.2 KB
eval/scripts/archive_run.pyexecutablescript9.1 KB
eval/scripts/codex_session.pyexecutablescript10.6 KB
eval/scripts/generate_dashboard.pyexecutablescript5.3 KB
eval/scripts/parse_artifacts.pyexecutablescript48.1 KB
eval/scripts/parse_session_logs.pyexecutablescript51.3 KB
eval/scripts/rescore_archived.pyexecutablescript5.5 KB
eval/scripts/score_campaign.pyexecutablescript43.8 KB
eval/scripts/snapshot_changes.pyexecutablescript11.1 KB
eval/scripts/verify_citations.pyexecutablescript8.8 KB
eval/tests/test_dashboard_bugs.pyexecutablescript8.8 KB
eval/tests/test_parse_session_logs.pyexecutablescript3.9 KB
eval/tests/test_parse_session_logs_round_inference.pyexecutablescript11.0 KB
eval/tests/test_score_campaign_diluted.pyexecutablescript9.4 KB
eval/viewer/dashboard_template.htmlexecutablescript15.1 KB
instrumentation/sitecustomize.pyexecutablescript3.6 KB
orchestration/audit-protocol.mdmarkdown9.3 KB
orchestration/debate-protocol.mdmarkdown11.2 KB
orchestration/integration-logic.mdmarkdown10.3 KB
orchestration/parallel-tracks.mdmarkdown8.9 KB
references/artifact-layout.mdexecutablescript22.4 KB
references/audit-invariants.mdmarkdown10.6 KB
references/champion-common-patterns.mdmarkdown3.4 KB
references/crossover-probing.mdexecutablescript4.7 KB
references/cudagraph-safety.mdmarkdown2.7 KB
references/debate-rules.mdmarkdown4.7 KB
references/debate-scoring-rubric.mdexecutablescript16.7 KB
references/e2e-delta-math.mdexecutablescript17.9 KB
references/e2e-latency-guide.mdexecutablescript9.6 KB
references/fusion-feasibility-heuristics.mdmarkdown5.6 KB
references/gpu-pool.mdexecutablescript5.4 KB
references/impl-track-rules.mdexecutablescript13.8 KB
references/nsys-profiling-guide.mdmarkdown9.8 KB
references/optimization-categories.mdexecutablescript11.0 KB
references/shutdown-protocol.mdexecutablescript3.1 KB
references/technology-selection.mdmarkdown5.0 KB
references/torch-compile-contract.mdmarkdown13.8 KB
references/validation-defaults.mdexecutablescript34.2 KB
references/workload-invocation.mdexecutablescript4.9 KB
references/writing-style.mdexecutablescript6.9 KB
scripts/ammo_state.pyexecutablescript142.0 KB
scripts/artifact_layout.jsonconfig16.3 KB
scripts/check_projection_accuracy.pyexecutablescript11.7 KB
scripts/create_evidence_template.pyexecutablescript9.7 KB
scripts/create_worktree_with_build.shexecutablescript10.2 KB
scripts/generate_validation_report.pyexecutablescript35.7 KB
scripts/gpu_reservation.pyexecutablescript27.1 KB
scripts/hook_cmd_classify.pyscript13.3 KB
scripts/mine_trace.pyscript29.4 KB
scripts/monitor_queue_ack.pyexecutablescript6.1 KB
scripts/ncu_sanity.shexecutablescript5.2 KB
scripts/ncu_sanity_driver.pyexecutablescript8.5 KB
scripts/new_target.pyexecutablescript22.0 KB
scripts/preflight_vllm_api.pyexecutablescript12.3 KB
scripts/reconcile_track_state.pyexecutablescript15.8 KB
scripts/remove_worktree_cleanup.shexecutablescript1.1 KB
scripts/resolve_codex_transcript.pyexecutablescript3.6 KB
scripts/run_vllm_bench_latency_sweep.pyexecutablescript249.6 KB
scripts/transcript_filter.pyexecutablescript38.4 KB
scripts/transitions.jsonexecutablescript1.5 KB
scripts/verify_validation_gates.pyexecutablescript88.8 KB
tests/agents/test-champion.mdexecutablescript20.4 KB
tests/agents/test-impl-champion.mdexecutablescript14.3 KB
tests/agents/test-implementer.mdexecutablescript15.8 KB
tests/agents/test-orchestrator.mdexecutablescript33.8 KB
tests/agents/test-researcher.mdexecutablescript21.0 KB
tests/agents/test-transcript-monitor.mdexecutablescript13.4 KB
tests/fixtures/diluted_pass/legacy_no_phase.golden.mdmarkdown1.1 KB
tests/fixtures/diluted_pass/legacy_no_phase.golden.summary.jsonconfig582 B
tests/fixtures/diluted_pass/legacy_no_phase.jsonconfig400 B
tests/fixtures/diluted_pass/legacy_scalar_phase.golden.mdmarkdown2.0 KB
tests/fixtures/diluted_pass/legacy_scalar_phase.golden.summary.jsonconfig1.0 KB
tests/fixtures/diluted_pass/legacy_scalar_phase.jsonconfig626 B
tests/fixtures/mining/real_campaign_bottleneck_analysis.mdmarkdown20.7 KB
tests/run_all.shexecutablescript1.6 KB
tests/scripts/test_transcript_filter.pyexecutablescript41.1 KB
tests/test_agent_runtime_contracts.pyexecutablescript1.8 KB
tests/test_ammo_state.pyexecutablescript71.7 KB
tests/test_artifact_layout_manifest.pyscript11.6 KB
tests/test_audit_started.pyscript18.2 KB
tests/test_correctness_comparator.pyscript12.6 KB
tests/test_diluted_pass.pyscript24.4 KB
tests/test_drift_compat.pyscript5.1 KB
tests/test_evidence_freshness.pyexecutablescript5.6 KB
tests/test_fail_closed.pyexecutablescript14.7 KB
tests/test_gpu_reservation.pyexecutablescript24.8 KB
tests/test_gpu_reservation_session_id.pyexecutablescript11.2 KB
tests/test_guidance_semantic_contract.pyscript24.9 KB
tests/test_hook_cmd_classify_parity.pyscript11.7 KB
tests/test_hook_semantics.pyexecutablescript95.3 KB
tests/test_mine_trace.pyscript24.2 KB
tests/test_mining_invalidated_schema.pyexecutablescript9.4 KB
tests/test_new_target_dp_ep.pyexecutablescript7.4 KB
tests/test_new_target_v2_scaffold.pyexecutablescript13.1 KB
tests/test_parse_artifacts.pyexecutablescript3.0 KB
tests/test_policy_convergence.pyscript797 B
tests/test_preflight_vllm_api.pyscript13.3 KB
tests/test_projection_accuracy_v2.pyexecutablescript4.1 KB
tests/test_reconcile_track_state.pyexecutablescript18.2 KB
tests/test_resolve_codex_transcript.pyexecutablescript3.1 KB
tests/test_state_schema_semantics.pyexecutablescript7.6 KB
tests/test_status_set_sync.pyexecutablescript9.1 KB
tests/test_sweep_baseline_from_arm.pyscript11.0 KB
tests/test_sweep_decode_capture.pyexecutablescript31.8 KB
tests/test_sweep_dp.pyexecutablescript45.4 KB
tests/test_sweep_fresh_cache.pyscript5.5 KB
tests/test_sweep_profiler_guard.pyscript22.6 KB
tests/test_sweep_real_prompts.pyscript20.1 KB
tests/test_sweep_refactor.pyexecutablescript37.6 KB
tests/test_sweep_round_slot.pyexecutablescript7.4 KB
tests/test_validation_report_phase_triage.pyexecutablescript10.0 KB
tests/test_validation_report_v2.pyexecutablescript6.2 KB
tests/test_verify_validation_gates.pyexecutablescript52.9 KB
tests/test_workload_matrix.pyexecutablescript19.3 KB

tests/test_new_target_dp_ep.py

View on GitHub
#!/usr/bin/env python3
# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: CC-BY-NC-4.0
"""TDD tests for DP / EP pass-through in new_target.py.

Covers:
  - --data-parallel-size flag on new_target.py
  - --enable-expert-parallel flag on new_target.py
  - Injection of --distributed-executor-backend external_launcher when DP > 1
  - Backward compatibility: defaults produce empty bench.extra_args
"""

from __future__ import annotations

import argparse
import json
import subprocess
import sys
from pathlib import Path

import pytest

# Ensure the scripts directory is importable (matches test_workload_matrix.py).
_SCRIPTS_DIR = Path(__file__).resolve().parent.parent / "scripts"
if str(_SCRIPTS_DIR) not in sys.path:
    sys.path.insert(0, str(_SCRIPTS_DIR))


def _make_fields(**overrides):
    """Build a TargetFields via _default_target_fields with test-friendly defaults.

    Mirrors the argparse.Namespace shape new_target.main() produces so we can
    exercise the JSON-composition logic directly without invoking argparse.
    """
    from new_target import _default_target_fields

    ns = argparse.Namespace(
        model_id="Qwen/Qwen3-Coder-480B",
        hardware="H100",
        dtype="fp8",
        tp=1,
        ep=1,
        max_model_len=4096,
        input_len=64,
        output_len=512,
        batch_sizes=[1, 8, 32],
        num_iters=5,
        noise_tolerance_pct=0.5,
        catastrophic_regression_pct=5.0,
        data_parallel_size=1,
        enable_expert_parallel=False,
    )
    for k, v in overrides.items():
        setattr(ns, k, v)
    return _default_target_fields(ns)


def _target_extra_args(**overrides):
    """Build TargetFields + run _target_json, return bench.extra_args list."""
    from new_target import _target_json

    fields = _make_fields(**overrides)
    out = _target_json(fields, Path("/tmp/fake_artifact_dir"))
    return out["bench"]["extra_args"]


class TestDefaults:
    """Backward compatibility: old callers with no DP/EP flags."""

    def test_defaults_no_dp_ep(self):
        """No DP/EP overrides → extra_args stays empty (backward compat)."""
        assert _target_extra_args() == []

    def test_dp_1_extra_args_empty(self):
        """Explicit --data-parallel-size 1 → no injection (DP=1 is single-process)."""
        assert _target_extra_args(data_parallel_size=1) == []


class TestDpInjection:
    """DP > 1 triggers auto-injection of external_launcher backend."""

    def test_dp_2_injects_backend(self):
        """--data-parallel-size 2 → DP flag + external_launcher backend, in order."""
        assert _target_extra_args(data_parallel_size=2) == [
            "--data-parallel-size", "2",
            "--distributed-executor-backend", "external_launcher",
        ]

    def test_dp_4_injects_backend(self):
        """Higher DP values stringify correctly."""
        assert _target_extra_args(data_parallel_size=4) == [
            "--data-parallel-size", "4",
            "--distributed-executor-backend", "external_launcher",
        ]


class TestEpFlag:
    """--enable-expert-parallel is independent of DP."""

    def test_enable_expert_parallel_only(self):
        """EP=True, DP=1 → only the EP flag in extra_args."""
        assert _target_extra_args(enable_expert_parallel=True) == [
            "--enable-expert-parallel",
        ]


class TestCombined:
    """DP and EP compose together. Order is deterministic: DP group first."""

    def test_dp_and_ep_compose(self):
        assert _target_extra_args(data_parallel_size=4, enable_expert_parallel=True) == [
            "--data-parallel-size", "4",
            "--distributed-executor-backend", "external_launcher",
            "--enable-expert-parallel",
        ]


class TestExistingFieldsUnaffected:
    """Regression: existing workload / target fields are not disturbed by DP/EP."""

    def test_dp_preserves_existing_tp_and_batch_sizes(self):
        from new_target import _target_json

        fields = _make_fields(tp=4, batch_sizes=[1, 8, 32], data_parallel_size=2)
        out = _target_json(fields, Path("/tmp/fake_artifact_dir"))

        assert out["target"]["tp"] == 4
        assert out["workload"]["batch_sizes"] == [1, 8, 32]
        assert out["bench"]["extra_args"] == [
            "--data-parallel-size", "2",
            "--distributed-executor-backend", "external_launcher",
        ]


class TestArgparseIntegration:
    """End-to-end: run new_target.py as a subprocess to catch argparse wiring bugs.

    Direct imports of _target_json bypass argparse, so dest=/action= typos
    in add_argument() would silently slip through. One subprocess invocation
    guards against that.
    """

    def test_cli_flags_produce_expected_extra_args(self, tmp_path):
        script = _SCRIPTS_DIR / "new_target.py"
        artifact_dir = tmp_path / "artifact"
        cmd = [
            sys.executable,
            str(script),
            "--artifact-dir", str(artifact_dir),
            "--model-id", "test-model",
            "--hardware", "H100",
            "--dtype", "fp8",
            "--tp", "2",
            "--data-parallel-size", "2",
            "--enable-expert-parallel",
        ]
        result = subprocess.run(cmd, capture_output=True, text=True)
        assert result.returncode == 0, f"stderr: {result.stderr}"

        target = json.loads((artifact_dir / "target.json").read_text())
        assert target["bench"]["extra_args"] == [
            "--data-parallel-size", "2",
            "--distributed-executor-backend", "external_launcher",
            "--enable-expert-parallel",
        ]


class TestStateJsonDpPersistence:
    """state.json must record dp parallelism alongside tp / ep."""

    def test_state_json_includes_dp_default_1(self):
        from new_target import _state_json

        fields = _make_fields()
        state = _state_json(fields, Path("/tmp/fake_artifact_dir"))
        assert state["target"]["dp"] == 1
        assert state["campaign"]["schema_version"] == "4.2"

    def test_state_json_includes_dp_when_set(self):
        from new_target import _state_json

        fields = _make_fields(tp=2, ep=1, data_parallel_size=4)
        state = _state_json(fields, Path("/tmp/fake_artifact_dir"))
        assert state["target"]["dp"] == 4
        assert state["target"]["tp"] == 2
        assert state["target"]["ep"] == 1

    def test_state_json_dp_via_argparse_subprocess(self, tmp_path):
        script = _SCRIPTS_DIR / "new_target.py"
        artifact_dir = tmp_path / "artifact"
        cmd = [
            sys.executable,
            str(script),
            "--artifact-dir", str(artifact_dir),
            "--model-id", "test-model",
            "--hardware", "H100",
            "--dtype", "fp8",
            "--tp", "2",
            "--data-parallel-size", "2",
        ]
        result = subprocess.run(cmd, capture_output=True, text=True)
        assert result.returncode == 0, f"stderr: {result.stderr}"

        state = json.loads((artifact_dir / "state.json").read_text())
        assert state["target"]["dp"] == 2
        assert state["target"]["tp"] == 2

    def test_state_schema_allows_legacy_missing_dp_but_defines_optional_dp(self):
        schema_path = _SCRIPTS_DIR.parents[2] / "schemas" / "state.schema.json"
        schema = json.loads(schema_path.read_text())
        target_schema = schema["properties"]["target"]
        assert "dp" not in target_schema["required"]
        assert target_schema["properties"]["dp"]["minimum"] == 1


if __name__ == "__main__":
    pytest.main([__file__, "-v"])
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
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: 194kUpdated Claude CodeCodexVerifiedInstall