Skip to main content
Exécutez n'importe quel Skill dans Manus
en un clic
amdpilot-org
Profil créateur GitHub

amdpilot-org

Vue par dépôt de 12 skills collectés dans 1 dépôts GitHub.

skills collectés
12
dépôts
1
mis à jour
2026-06-30
carte des dépôts

Où se trouvent les skills

Principaux dépôts par nombre de skills collectés, avec leur part dans ce catalogue créateur et leur couverture métier.

explorateur de dépôts

Dépôts et skills représentatifs

run-value-summary
Développeurs de logiciels

Emit a structured RUN_SUMMARY v1 block at the end of any scored run so the reviewer (human or LLM judge) can decide whether to invest more on this lineage. Use when a run produced measurable outcomes (benchmark, accuracy, speedup, rocprof). Skip it when the run is a trivial bugfix or port-that- just-compiles with no scoring signal.

2026-06-30
flydsl-kernel-authoring
Développeurs de logiciels

FlyDSL is a Python DSL with MLIR-native backend for authoring custom AMD GPU kernels with explicit layout algebra (pre-installed at /opt/FlyDSL on images tagged *-flydsl:*). Use this skill when profiling identifies a hot per-row reduction (RMSNorm / LayerNorm / softmax), a fused elementwise chain (norm + residual add, activation + multiplier), or an unusual-shape grouped GEMM that the standard AMD backends (Triton / aiter / CK / hipBLASLt / TransformerEngine) don't serve well. Essential for any workload where Python/config/Triton-tuning gains have plateaued and the profile shows a custom kernel opportunity. Covers the `/opt/FlyDSL` availability check, the integration playbook (dispatcher + direct site-packages edit + autograd-safe output handling), kernel authoring patterns (elementwise via layout API, block reductions via wave_reduce_add, fused dx+dw designs, MFMA GEMM preshuffle), torchrun gotchas, and the critical rule that custom kernels typically only win end-to-end when stacked with `torch.compile(mode=

2026-04-29
amd-kernel-optimization
Développeurs de logiciels

Optimize inference latency and throughput of PyTorch models on AMD GPUs (MI250/MI300/MI350) with ROCm. Use when profiling and optimizing GEMM, attention, elementwise ops, torch.compile, CUDAGraphs, or Triton kernels on AMD hardware. Covers the full optimize cycle: benchmark → profile → analyze → implement → verify. Also covers benchmarking methodology and common pitfalls that waste time.

2026-04-25
rocm-profiler-analysis
Développeurs de logiciels

Analyze SGLang and vLLM profiler traces on AMD ROCm systems, especially MI355X/gfx950 nodes. Adapted from the SGLang torch-profiler workflow: triage kernel breakdown, overlap headroom, and fuse opportunities, then write structured artifacts that can be attached to amdpilot experiments, trials, and dashboard views. Use when a run needs profiling, when an optimization trial should produce machine-readable profiling artifacts, or when the user asks why a ROCm workload is slow.

2026-04-01
auto-benchmark-rocm
Développeurs de logiciels

Run AI-driven benchmark searches on AMD ROCm with tiered server-flag sweeps for vLLM/SGLang, canonical dataset preparation, SLA or fixed-QPS benchmarking, CSV export, and resume. Adapted from SGLang auto-benchmark for MI355X (gfx950) / MI300X (gfx942) on ROCm 7.x. Use when the user wants an automated benchmark workflow on AMD GPUs rather than a one-off bench_serving command. Integrates with amdpilot executor task_spec_json for resource-aware launch.

2026-04-01
amd-ci-test-bisect
Analystes en assurance qualité des logiciels et testeurs

Add or update AMD/ROCm SGLang regression tests, choose the right MI325/MI35x CI suite, reproduce AMD CI locally with the upstream amd_ci container scripts, and bisect AMD CI regressions on main/nightly. Use when an agent-generated fix needs register_amd_ci coverage, when selecting MI325 vs MI35x runners, when debugging pr-test-amd or nightly AMD failures, or when documenting the register_amd_ci flow for ROCm-specific fixes.

2026-04-01
rocm-crash-debug
Développeurs de logicielsAnalystes en assurance qualité des logiciels et testeurs

Debug ROCm/HIP kernel crashes in SGLang and vLLM on AMD GPUs (MI300X/MI325X/MI355X). Adapts SGLang's @debug_kernel_api kernel boundary logging to ROCm: captures input tensors before crash, tracks shapes/dtypes/values, dumps crash artifacts for offline analysis. Integrates with amdpilot executor failure_reason field and dashboard trajectory viewer. Triggered by: CUDA/HIP errors, illegal memory access, device-side assert, OOM kills, signal 137/139, NaN/Inf in outputs, "debug crash", "why did the trial fail".

2026-04-01
amd-rocm-porting
Développeurs de logiciels

Port NVIDIA CUDA codebases to AMD ROCm GPUs. Use when making PyTorch models run on AMD GPUs, replacing NVIDIA-specific libraries with AMD equivalents, fixing ROCm build/runtime failures, or porting C/C++ CUDA kernels to HIP. Also covers dependency debugging and environment setup on ROCm Docker images.

2026-02-26
Affichage des 8 principaux skills collectés sur 12 dans ce dépôt.
1 dépôts affichés sur 1
Tous les dépôts sont affichés