메뉴
SkillsMP는 Xilinx/mlir-air에서 15개의 skill을 수집했습니다. skill을 열어 소스와 세부 정보를 확인하세요.
수집된 skill 15개 중 15개를 표시합니다.
Use when an NPU kernel passes its standalone shape test but produces NaN, garbage, or stale values when invoked as part of a larger pipeline. Common symptoms: correct first invocation but wrong on subsequent calls; correct in isolation but wrong when chained…
원문 언어: 영어
Use when NPU FlashAttention hangs (`ERT_CMD_STATE_TIMEOUT`) or produces NaN at head_dim ≥ 128. Discriminates the three known root causes (compile-flag mismatch, seq-first dk_chunks bug, true L1 overflow) via a symptom-classification table and applies the…
원문 언어: 영어
Use when stitching kernels into a multi-launch ELF and the AIE compiler rejects the merged module (BD exhaustion, channel routing, herd shape conflict, IR validation error, DMA stride limitation). Discriminates the 6 known compile blockers via a…
원문 언어: 영어
Entry point for deploying a new decoder-only LLM on AMD NPU2. Invoked by the user as `/deploy-new-llm <hf_model_id> [--name <dirname>] [--target npu2|npu1] [--dtype bf16|fp16]`. Bootstraps the per-model workspace, validates architecture is in scope, and…
원문 언어: 영어
Optimization skill — reuse NPU BufferObjects across calls instead of re-allocating/re-writing them. Two mechanics in one class: (B1) per-layer weight BOs pre-loaded once and skipped via static_input_indices, and (B2) intermediate BOs the kernel overwrites,…
원문 언어: 영어
Optimization skill — choose activation layouts so consecutive kernels hand off on-device without a host-side transpose. Canonical case: seq-first (seq, n_heads·head_dim) so RMSNorm → RoPE → FlashAttention → O-proj stay seq-first, eliminating 1–4 host…
원문 언어: 영어
Procedural recipe for fusing multiple `air.launch` kernels into one multi-launch ELF (single XRT invocation). Invoked by phase-4-prefill-optimization and phase-5-decode-optimization to fuse kernel groups when building NEW model-specific fused ELFs…
원문 언어: 영어
Phase 0 of LLM deployment — produce `<model>_weights.py` (HF weight loader) and `<model>_cpu_helpers.py` (the few NumPy helpers production prefill/decode import), then confirm the HF bf16 reference baseline loads and runs via the shared…
원문 언어: 영어
Phase 1 of LLM deployment — for every leaf kernel × shape the model needs, verify numerical correctness on real NPU2 against the registry's GPU/vLLM-aligned standard. Primary gate where a standalone harness exists: the harness's full-output element-wise…
원문 언어: 영어
Phase 2 of LLM deployment — wire the verified Phase 1 kernels into one transformer block on NPU and verify per-layer cosine vs the HF bf16 reference (the shared `programming_examples/llms/verify/` diagnosis lens, promoted to a gate at layer 0). Catches…
원문 언어: 영어
Phase 3 of LLM deployment — wire all N layers and verify NPU matches the HF bf16 reference end-to-end (per-layer cosine via the shared `programming_examples/llms/verify/` diagnosis lens + token-level top-5 set-inclusion via its token-set gate) at canonical…
원문 언어: 영어
Phase 4 of LLM deployment — apply the shared optimization skillset to a Phase-3-correct prefill pipeline (multi-launch merge, BO pre-loading + intermediate buffer reuse, seq-first layout). Thin orchestrator that dispatches `opt-merge-multi-launch-kernels`,…
원문 언어: 영어
Phase 5 of LLM deployment — apply the shared optimization skillset to a Phase-4-correct decode pipeline (multi-launch merge with N-way extern rename, static weight BOs, on-device layout). Thin orchestrator that dispatches `opt-merge-multi-launch-kernels`,…
원문 언어: 영어
Phase 6 of LLM deployment — integrate Phase 4 prefill + Phase 5 decode into a clean `<model>_inference.py`, write the model's `verify_adapter.py` hooking into the shared `programming_examples/llms/verify/` subsystem + a Makefile (run / verify / verify-full /…
원문 언어: 영어
Phase 7 of LLM deployment — spawn a fresh subagent that treats the deployment as UNTRUSTED, audits the `make verify` implementation (anti-reward-hacking: confirms the token-set gate runs the production path vs HF bf16), then re-runs it as the primary gate.…
원문 언어: 영어