By mirage-project

Runtime-V2 performance-iteration workflow. An agent skill from mirage-project/mirage.

mirage-project/mirage

Step-by-step guide for adding a new task implementation to Mirage Persistent Kernel (MPK).

mirage-project/mirage

A skill your agent uses when the user wants to design or extend a FlashAttention-style forward kernel on B200/Blackwell, involving the two MMAs QKᵀ and PV, online softmax, S/P/O in TMEM, warp roles…

mirage-project/mirage

Build or run a FAITHFUL in-MPK per-task latency gate (slowCTA at the production grid + cos) for a DeepSeek-V3 MPK decode kernel or shape.

mirage-project/mirage

A skill your agent uses when a batch of env-gated (ifdef MPKDSV3 / os.environ-controlled, default-OFF) MPK optimization levers needs to be consolidated into a single clean code path for a PR…

mirage-project/mirage

Guide for using MPK test mode to unit-test individual layers or multi-layer pipelines through the full compilation pipeline.

mirage-project/mirage

End-to-end pipeline for adding or porting a model to MPK Runtime-V2 — from a compute-graph spec (shapes + draw.io graph + HF checkpoint + TP/EP plan) to a working multi-GPU demo.

mirage-project/mirage

Runtime-V2 kernel-writing workflow. An agent skill from mirage-project/mirage.

mirage-project/mirage

Reference guide for the MPK compilation-to-runtime pipeline.

mirage-project/mirage

Guide for adding a new model (e.g., Llama4, DeepSeek V3) to the MPK persistent kernel.

mirage-project/mirage

A skill your agent uses when the user wants to use Thread Block Cluster, DSMEM, 2-CTA cooperative MMA, persistent kernels, a tile scheduler, or Cluster Launch Control on B200 to handle uneven tails.

mirage-project/mirage

A skill your agent uses when the user wants to implement from scratch, port, or systematically optimize a B200/Blackwell GEMM.

mirage-project/mirage

A skill your agent uses when the user asks "why is this B200/Blackwell kernel slow, what should I optimize first, should I fuse or move to Tensor Cores/TMA".

mirage-project/mirage

A skill your agent uses when a B200/Blackwell kernel shows wrong results, uncoalesced global memory access, SMEM bank conflicts, a TMA swizzle that mismatches the Tensor Core read, or confused…

mirage-project/mirage

A skill your agent uses when a Blackwell/B200 asynchronous kernel deadlocks, fails intermittently, reads stale data, reuses a stage too early, or when the arrival, tx-count, phase, and wait of…

mirage-project/mirage

A skill your agent uses when the user wants to map an ML operator onto a B200/Blackwell kernel, or to review which threads should execute a given tile primitive, where the data should live, and…

mirage-project/mirage

A skill your agent uses when the user needs to choose the tile, dtype, ctagroup::1/2, SMEM operand layout, or TMEM accumulator mapping for a tcgen05 MMA on B200/Blackwell, or to implement an…

mirage-project/mirage

A skill your agent uses when the user wants to convert regular GMEM↔SMEM tile copies to TMA on B200/Blackwell, design double-buffered/multi-stage pipelines, choose a swizzle, or distinguish the TMA…

mirage-project/mirage

A skill your agent uses when the user is using tcgen05 on Blackwell/B200 and needs to plan TMEM accumulators, block-scale factors, TMEM column allocation, the tcgen05.ld/st/cp paths, epilogue…

mirage-project/mirage

A skill your agent uses when a B200/TIRx/CUDA warp-specialized kernel fails to compile, deadlocks, hits an illegal memory access, produces wrong results, or is "correct but slow".

mirage-project/mirage

A skill your agent uses when the user wants to confirm whether an existing CUDA extension/binary can run on B200, configure compute100/sm100 or the architecture-specific sm100a, or check PTX/cubin…

mirage-project/mirage

Audit the DeepSeek V3 MPK demo + builder chain end-to-end and confirm logical equivalence with vLLM's reference implementation.

mirage-project/mirage

A skill your agent uses when you need a NEW or optimized MPK CUDA kernel (a per-task .cuh under include/mirage/persistentkernel/tasks/) that must PROVABLY beat a target WITHOUT the kernel-optimizer…

mirage-project/mirage

The MPK team's "where does a change belong + what a clean PR looks like" norms, extracted from mirage-project/mpk merged-PR history.

mirage-project/mirage