SqueezeAILab

icon indicating a website link https://people.eecs.berkeley.edu/~keutzer/

icon location SqueezeAI is part of Berkeley AI Research Lab at UC Berkeley focused on AI Systems research.

Results 4 repositories owned by SqueezeAILab

SqueezeLLM

577
Stars
37
Forks
Watchers

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

verified publisher icon SqueezeAILab

LLMCompiler

1.1k
Stars
80
Forks
Watchers

[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling

verified publisher icon SqueezeAILab

KVQuant

212
Stars
16
Forks
Watchers

KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

verified publisher icon SqueezeAILab

LLM2LLM

116
Stars
8
Forks
Watchers

[ACL 2024] LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement

verified publisher icon SqueezeAILab