Eric Auld's repositories
flash-attention
Fast and memory-efficient exact attention
cccl
CUDA Core Compute Libraries
Language:C++NOASSERTION000
Language:C++000
cutlass
CUDA Templates for Linear Algebra Subroutines
Language:C++NOASSERTION000
flashinfer
FlashInfer: Kernel Library for LLM Serving
Language:CudaApache-2.0000
fp6_llm
An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
Language:CudaApache-2.0000
Language:C++Apache-2.0000
qmk_firmware
QMK, forked for ZSA's Oryx Configurator (to safeguard stability)
Language:CGPL-2.0000
QuIP
Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"
Language:Python000
Language:PythonGPL-3.0000
resource-stream
CUDA related news and material links
MIT000
Sequoia
scalable and robust tree-based speculative decoding algorithm
Language:Python000
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Apache-2.0000