speculative-decode

N-gram draft-then-verify for trading LLM text (NVIDIA FORMAT). Measure AL. Do not vendor TensorRT-LLM or train EAGLE. Slash: /speculative-decode.

Related in development

update-docs-vercel-next-js

This skill should be used when the user asks to "update documentation for my changes", "check docs for this PR", "what d...

by vercel
137,316

docstring-pytorch-pytorch

Write docstrings for PyTorch functions and methods following PyTorch conventions. Use when writing or updating docstring...

by pytorch
96,875

at-dispatch-v2

Convert PyTorch AT_DISPATCH macros to AT_DISPATCH_V2 format in ATen C++ code. Use when porting AT_DISPATCH_ALL_TYPES_AND...

dispatch
by pytorch
95,362