llm inference commands

quantumaikr/quant.cpp

Command Claude Code

Launch the hierarchical harness (Karpathy loop + ClawTeam parallel agents).

quantumaikr/quant.cpp

Command Claude Code

Merge worker branches one-by-one with score-based accept/reject.

quantumaikr/quant.cpp

Command Claude Code

Spawn ClawTeam parallel workers for the current development phase.

webgptorg/promptbook

Command

Expect command describes the desired output of the task (after post-processing).

webgptorg/promptbook

Command

Format command describes the desired output of the task (after post-processing).

webgptorg/promptbook

Command

Defines the purpose of the markdown section - if its a task and which type or something else.

RightNow-AI/AutoMegaKernel

Command Claude Code

Launch the unattended / overnight AMK autoresearch driver on $ARGUMENTS (model [gpu] [minutes|iters]).

RightNow-AI/AutoMegaKernel

Command Claude Code

One-shot compile + verify a model into a CUDA megakernel via amk compile on $ARGUMENTS (model [gpu]).

RightNow-AI/AutoMegaKernel

Command Claude Code

Drive an interactive AMK propose -> eval -> keep/revert megakernel schedule session on $ARGUMENTS (model [gpu]).

cloudrift-ai/emmy

Command

Command "ARCHITECTURE" from cloudrift-ai/emmy, covering commands architecture, layered design, layers, emmy/recipe/ — recipe library and emmy/deploy/ — deploy library.

John-Wendell/Attention-MoA

Command

Command "conv_release" from John-Wendell/Attention-MoA, covering chatbot arena conversations, all conversations and prompt distribution.

John-Wendell/Attention-MoA

Command

Command "data_cleaning" from John-Wendell/Attention-MoA, covering data cleaning, requirements, steps, convert html to markdown and keep or remove specific languages.

John-Wendell/Attention-MoA

Command

Command "pypi" from John-Wendell/Attention-MoA, covering requirement and upload.