Sid Jha's repositories
Megatron-LM-Benchmarks
Benchmarks of NVIDIA's Megatron-LM
alpa
Training and serving large-scale neural networks with auto parallelization.
BigLittleDecoder
[NeurIPS'23] Speculative Decoding with Big Little Decoder
ColossalAI
Making big AI models cheaper, easier, and more scalable
DiskANN
Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search
dspy
DSPy: The framework for programming—not prompting—foundation models
lmql
A programming language for large language models.
TinyAgent
TinyAgent: Function Calling at the Edge!
NeuralDB
Database Reasoning Over Text project for ACL paper
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
SqueezeLLM
SqueezeLLM: Dense-and-Sparse Quantization
zero_scrolls
Running inference on the ZeroSCROLLS benchmark