answerdotai Goto Github PK

.github

ao

Native PyTorch library for quantization and sparsity

bert24

bitlora

Experimental q[X]ora kernel development code

bitsandbytes

8-bit CUDA functions for PyTorch

claudette

Claudette is Claude's friend

cold-compress

Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of GPT-Fast, a simple, PyTorch-native generation codebase.

cosette

Claudette's sister, a helper for OpenAI GPT

css-scope-inline

🌘 Scope your inline style tags in pure vanilla CSS! Only 16 lines. No build. No dependencies.

dawn-artifacts

efficient-attn

Experiments using Efficient AttentionCLA, MH Latent Attention, GIST, Local-Global, Landmark Attention, YOCO)

fasthtml

The fastest way to create an HTML app

fasthtml-example

Example fasthtml applications demonstrating a range of web programming techniques

fasthtml-gallery

fasthtml-hf

Huggingface deployment for FastHTML

fasthtml-js

Javascript for FastHTML apps

fasthtml-tut

Code to go with beginner FastHTML tutorial

fastlite

A bit of extra usability for sqlite

fastmenu

Extension library to fasthtml that makes it very simple to create custom context menus

fastsql

fh-about

about.fastht.ml source

fh-bootstrap

fasthtml wrapper for bootstrap

fh-deploy

Deployment examples for FastHTML

fh-flowbite

fh-fomanticui

fsdp_qlora

Training LLMs with QLoRA + FSDP

gpu.cpp

A lightweight library for portable low-level GPU computation using WebGPU.

gpu.cpp-website

home-fasthtml

hqq

Official implementation of Half-Quadratic Quantization (HQQ)