Andre Slavescu's repositories
pokemon-showdown
Pokémon battle simulator.
AIR-Bench
AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark
Awesome-LLM-Inference
📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.
awesomeMLSys
An ML Systems Onboarding list
BitBLAS
BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.
chameleon
Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.
ChatTTS
ChatTTS is a generative speech model for daily dialogue.
efficient-kan
An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).
fiddler
Fast Inference of MoE Models with CPU-GPU Orchestration
llamafile
Distribute and run LLMs with a single file.
llm.c
LLM training in simple, raw C/CUDA
open-interpreter
A natural language interface for computers
pyserini
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
pytensor
PyTensor allows you to define, optimize, and efficiently evaluate mathematical expressions involving multi-dimensional arrays.
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
ROCm
AMD ROCm™ Software - GitHub Home
Samba
Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"
SLAMesh
The official implementation of SLAMesh.
SpeculativeDecodingPapers
📰 Must-read papers and blogs on Speculative Decoding ⚡️
ThunderKittens
Tile primitives for speedy kernels
vision
Datasets, Transforms and Models specific to Computer Vision