Merge branch 'main' into dholanda/tl_pull

Author: danielholanda

.github/scripts/import_external_skills.py

@@ -30,6 +30,11 @@
 Usage:
     uv run .github/scripts/import_external_skills.py            # write changes
     uv run .github/scripts/import_external_skills.py --dry-run  # report only
+    uv run .github/scripts/import_external_skills.py --only magpie  # one skill
+
+The `--only` flag (repeatable) restricts the run to the named skill
+folder(s): other skills in the catalog are skipped and pruning is limited
+to the named skills, so unrelated federated skills are never removed.
 
 The companion GitHub Actions workflow `import-external-skills` calls this
 script on manual dispatch and opens a pull request with the result.
@@ -553,9 +558,33 @@ def main(argv: list[str] | None = None) -> int:
         default=CATALOG_FILE,
         help=f"Path to the catalog file (default: {CATALOG_FILE}).",
     )
+    parser.add_argument(
+        "--only",
+        action="append",
+        metavar="SKILL",
+        help=(
+            "Import only the named skill folder (repeatable). When set, "
+            "skills not named here are left untouched and pruning is "
+            "restricted to the named skills, so other federated skills are "
+            "never removed."
+        ),
+    )
     args = parser.parse_args(argv)
 
     sources = parse_sources(args.catalog)
+
+    only = set(args.only or [])
+    if only:
+        known = {spec.folder for source in sources for spec in source.skills}
+        unknown = only - known
+        if unknown:
+            raise ValueError(
+                "--only names skill(s) not present in the catalog: "
+                + ", ".join(sorted(unknown))
+            )
+        for source in sources:
+            source.skills = [s for s in source.skills if s.folder in only]
+        sources = [source for source in sources if source.skills]
     log: list[str] = []
     declared: set[str] = set()
     all_results: list[ImportResult] = []
@@ -573,7 +602,15 @@ def main(argv: list[str] | None = None) -> int:
             declared.add(spec.folder)
         all_results.extend(import_source(source, args.dry_run, log))
 
-    pruned = prune_orphans(declared, existing_federated, args.dry_run, log)
+    # With --only we deliberately ignore skills the user didn't name, so
+    # restrict orphan pruning to just those skills. Otherwise every other
+    # federated skill would look like an orphan and be deleted.
+    prunable = (
+        {name: marker for name, marker in existing_federated.items() if name in only}
+        if only
+        else existing_federated
+    )
+    pruned = prune_orphans(declared, prunable, args.dry_run, log)
     marketplace_changed = update_marketplace(all_results, args.dry_run)
 
     for line in log:

skills/magpie/.federated.json

@@ -2,8 +2,8 @@
   "source": "amd-agi-magpie",
   "repo": "AMD-AGI/Magpie",
   "ref": "main",
-  "commit": "2a9263833f71755df2a93b466cdd3a9f803fc625",
+  "commit": "02d9a7dfc3aedec0e3feadb7449f6c0c318621d5",
   "path": "skills/magpie",
   "license": "MIT",
-  "imported_at": "2026-05-28T21:37:43Z"
+  "imported_at": "2026-06-18T20:31:36Z"
 }

skills/magpie/SKILL.md

@@ -37,7 +37,7 @@ magpie analyze path/to/kernel.hip --testcase "./run_test.sh"
 - `--no-perf`: Skip performance profiling.
 - `-o`, `--output-dir`: Output directory (default: `./results`).
 
-**Config template (single kernel):** Use `kernel:` with `id`, `type`, `source_files`, `working_dir`, `testcase_command`, optional `compile_command`, `env`. See [Magpie/kernel_config.yaml.example](https://github.com/AMD-AGI/Magpie/blob/2a9263833f71755df2a93b466cdd3a9f803fc625/Magpie/kernel_config.yaml.example) and [examples/ck_gemm_add.yaml](https://github.com/AMD-AGI/Magpie/blob/2a9263833f71755df2a93b466cdd3a9f803fc625/examples/ck_gemm_add.yaml).
+**Config template (single kernel):** Use `kernel:` with `id`, `type`, `source_files`, `working_dir`, `testcase_command`, optional `compile_command`, `env`. See [Magpie/kernel_config.yaml.example](https://github.com/AMD-AGI/Magpie/blob/02d9a7dfc3aedec0e3feadb7449f6c0c318621d5/Magpie/kernel_config.yaml.example) and [examples/ck_gemm_add.yaml](https://github.com/AMD-AGI/Magpie/blob/02d9a7dfc3aedec0e3feadb7449f6c0c318621d5/examples/ck_gemm_add.yaml).
 
 ## Compare (multiple kernels)
 
@@ -59,7 +59,7 @@ magpie compare kernel1.hip kernel2.hip --testcase "./run_test.sh"
 - `--baseline`: Index of baseline kernel (default: 0).
 - `--no-perf`, `-o`: Same as analyze.
 
-Example: [examples/ck_grouped_gemm_compare.yaml](https://github.com/AMD-AGI/Magpie/blob/2a9263833f71755df2a93b466cdd3a9f803fc625/examples/ck_grouped_gemm_compare.yaml).
+Example: [examples/ck_grouped_gemm_compare.yaml](https://github.com/AMD-AGI/Magpie/blob/02d9a7dfc3aedec0e3feadb7449f6c0c318621d5/examples/ck_grouped_gemm_compare.yaml).
 
 ## Benchmark (vLLM / SGLang)
 
@@ -81,7 +81,7 @@ magpie benchmark --benchmark-config examples/benchmarks/benchmark_vllm_dsr1.yaml
 - `--run-mode`: `docker` (default) or `local`.
 - `--docker-image`, `--timeout`, `-o`: Override image, timeout (seconds), output dir.
 
-Example configs: [examples/benchmarks/benchmark_vllm_dsr1.yaml](https://github.com/AMD-AGI/Magpie/blob/2a9263833f71755df2a93b466cdd3a9f803fc625/examples/benchmarks/benchmark_vllm_dsr1.yaml), [docs/benchmark.md](https://github.com/AMD-AGI/Magpie/blob/2a9263833f71755df2a93b466cdd3a9f803fc625/docs/benchmark.md).
+Example configs: [examples/benchmarks/benchmark_vllm_dsr1.yaml](https://github.com/AMD-AGI/Magpie/blob/02d9a7dfc3aedec0e3feadb7449f6c0c318621d5/examples/benchmarks/benchmark_vllm_dsr1.yaml), [docs/how-to/benchmark.md](https://github.com/AMD-AGI/Magpie/blob/02d9a7dfc3aedec0e3feadb7449f6c0c318621d5/docs/how-to/benchmark.md).
 
 ## Gap analysis (standalone)
 
@@ -109,7 +109,7 @@ Shows vendor, architecture, compiler, profiler. No mode required.
 
 When the user needs a kernel config file:
 
-1. Emit YAML matching the structure in [Magpie/kernel_config.yaml.example](https://github.com/AMD-AGI/Magpie/blob/2a9263833f71755df2a93b466cdd3a9f803fc625/Magpie/kernel_config.yaml.example): `kernel:` with `id`, `type` (hip|cuda|pytorch), `source_files`, `working_dir`, `testcase_command`, and optionally `compile_command`, `env`.
+1. Emit YAML matching the structure in [Magpie/kernel_config.yaml.example](https://github.com/AMD-AGI/Magpie/blob/02d9a7dfc3aedec0e3feadb7449f6c0c318621d5/Magpie/kernel_config.yaml.example): `kernel:` with `id`, `type` (hip|cuda|pytorch), `source_files`, `working_dir`, `testcase_command`, and optionally `compile_command`, `env`.
 2. Write the file to the user's requested path (e.g. `kernel_config.yaml`).
 3. Run: `magpie analyze --kernel-config <that_file>`.
 

skills/magpie/reference.md

@@ -100,4 +100,4 @@ kernels:
 
 ## Benchmark config YAML
 
-Top-level key `benchmark:` with `framework`, `model`, `precision`, `envs`, `profiler`, `gap_analysis`, `timeout_seconds`, etc. See `examples/benchmarks/benchmark_vllm_dsr1.yaml` and `docs/benchmark.md`.
+Top-level key `benchmark:` with `framework`, `model`, `precision`, `envs`, `profiler`, `gap_analysis`, `timeout_seconds`, etc. See `examples/benchmarks/benchmark_vllm_dsr1.yaml` and `docs/how-to/benchmark.md`.

skills/magpie/skill-card.md

@@ -2,7 +2,7 @@
 
 ## Description
 
-Perform GPU kernel correctness and performance evaluation and LLM inference benchmarking with Magpie (HIP/CUDA/PyTorch kernels, vLLM/SGLang benchmarks, TraceLens, and torch-trace gap analysis).
+Performs GPU kernel correctness and performance evaluation and LLM inference benchmarking with Magpie. Analyzes single or multiple kernels (HIP/CUDA/PyTorch), compares kernel implementations, runs vLLM/SGLang benchmarks with profiling and TraceLens, and runs gap analysis on torch traces.
 
 ## Owner