appoose's Stars
dottxt-ai/outlines
Structured Text Generation
MahmoudAshraf97/whisper-diarization
Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper
leptonai/search_with_lepton
Building a quick conversation-based search demo with Lepton AI.
mobiusml/gemlite
Fast low-bit matmul kernels in Triton
linkedin/Liger-Kernel
Efficient Triton Kernels for LLM Training
mobiusml/aana_sdk
Aana SDK is a powerful framework for building AI enabled multimodal applications.
IST-DASLab/marlin
FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
AnswerDotAI/fsdp_qlora
Training LLMs with QLoRA + FSDP
Maykeye/hqq-memory-efficient-quantization
Script for HQQification of mixtral from HF's shards
dvmazur/mixtral-offloading
Run Mixtral-8x7B models in Colab or consumer desktops
mobiusml/hqq
Official implementation of Half-Quadratic Quantization (HQQ)
Fuzzy-Search/realtime-bakllava
llama.cpp with BakLLaVA model describes what does it see
AI-Yash/st-chat
Streamlit Component, for a Chatbot UI
eyeem/scala-flume-client
A tiny Scala library to send events and entities to Apache Flume.
songhan/SqueezeNet-Deep-Compression
appoose/crawlForImages
Crawl popular image search engines ( google, bing, 500px , flickr ) for images given a query
sightio/tornado-api-kit
A collection of routines for building web APIs on top of Tornado web server.