Use when working on or testing imp-server and its HTTP APIs — OpenAI/Anthropic endpoints, /v1/chat/completions, /v1/messages, SSE streaming, tool calling, json_schema/constrained decoding, thinking/reasoning_content, cache_control/prefix cache, model loading semantics, "server returns 404/garbage", API compliance. Do NOT use for CLI-only inference (imp-cli), kernel work (sm120-cuda-expert), or pure output-quality checks (check-degeneration).
Use when benchmarking, profiling, or A/B-testing CUDA kernels or end-to-end perf in the imp inference engine on RTX 5090 (sm_120), including refreshing tests/perf_baseline.json or publishing numbers to docs/BENCHMARKS.md and the README. Triggers on "benchmark kernel", "profile cuda", "ncu", "nsys", "kernel timing", "occupancy", "bandwidth bound", "compute bound", "roofline", "perf baseline", "is this regression real", "decode dropped". Do NOT use for writing/optimizing kernel code (sm120-cuda-expert) or output-quality checks (check-degeneration).
Use when writing, reviewing, or optimizing CUDA kernels targeting sm_120a (RTX 5090 / Consumer Blackwell, GB202) in the imp inference engine. Triggers on CUDA/PTX kernel code, shared-memory layout, tensor-core MMA, GEMV/GEMM/attention/quantization kernels, decode tok/s under expected, kernel emitting HMMA instead of mxf4nvf4, occupancy or register-pressure questions. Pair with `benchmark-cuda` for measurement and `check-degeneration` after hot-path changes.
Use when working on imp's quantization formats, loaders, or dequant paths — GGUF Q4_0…Q8_0/Q*_K/IQ4/MXFP4, NVFP4 two-level scaling, FP8 E4M3, StorageTier, decode cache, KV-cache dtypes, "which quant should I use", scale-factor layout, dequant kernel wiring. Do NOT use for writing/optimizing GEMM/GEMV kernels (sm120-cuda-expert) or measuring quant perf (benchmark-cuda).
Use when building imp, running its test suite, checking CI status, or debugging build/test failures — "make build", "run the tests", "test-gpu", "verify-fast", GTEST_FILTER, Docker/CUDA toolchain, dependency bumps, "CI is red/blocked", determinism or perplexity checks. Do NOT use for benchmarking/profiling (benchmark-cuda) or output-quality batteries (check-degeneration).
Use when verifying that a model in the imp inference engine produces coherent output without repetition loops, token-stuck states, or state corruption across turns. Triggers on "degenerates", "check degeneration", "repetition loop", "own own own", "stuck token", "multi-turn regression", "does it still work", and after enabling CUDA graphs / changing forward pass / MoE routing / KV cache / GDN state.
Use when adding support for a new model architecture to imp, porting a model family, or debugging a model that loads but produces wrong output — "add support for <model>", "new arch", loader detection, chat template, RoPE variant, "outputs garbage", "prompt-blind", "digits scrambled", "NaN logits". Do NOT use for kernel performance (sm120-cuda-expert) or quant-format questions (quant-formats).
Use when auditing the imp codebase for structural debt, dead code, god-objects/files, duplication, flag sprawl, or deciding whether a cleanup is worth shipping — "structure audit", "tech debt", "is this still used", "dead code", "refactor for clarity", "should we split this file", "remove this flag". Do NOT use for build/test mechanics (building-and-testing), perf/kernel work (benchmark-cuda / sm120-cuda-expert), or output quality (check-degeneration).