changwoolee/BLAST
[NeurIPS 2024] BLAST: Block Level Adaptive Structured Matrix for Efficient Deep Neural Network Inference
This project helps machine learning engineers and researchers make large deep neural networks, like Llama-7B, run faster and more efficiently. It takes an existing large language model and applies a compression technique to create a smaller, optimized version. The outcome is a model that performs comparably but requires less computational power for inference.
No commits in the last 6 months.
Use this if you need to deploy large language models on resource-constrained hardware or reduce the operational costs of running AI inference.
Not ideal if you are a data scientist or business user looking for a ready-to-use application rather than a technical solution for model optimization.
Stars
17
Forks
1
Language
Python
License
MIT
Category
Last pushed
Nov 06, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/changwoolee/BLAST"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
sgl-project/sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
alibaba/MNN
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering...
xorbitsai/inference
Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source,...
tensorzero/tensorzero
TensorZero is an open-source stack for industrial-grade LLM applications. It unifies an LLM...