SqueezeAILab

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

Pinned Repositories

KVQuant
[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
Language:Python307 13 1526
LLM2LLM
[ACL 2024] LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement
Language:Python155 6 610
LLMCompiler
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
Language:Python1.5k 25 7111
open_source_projects
Open Source Projects from Pallas Lab
20 3 02
SqueezeLLM
[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
Language:Python651 18 2743
TinyAgent
[EMNLP 2024 Demo] TinyAgent: Function Calling at the Edge!
Language:Python313 10 651
Tool2Vec
Efficient and Scalable Estimation of Tool Representations in Vector Space
Language:Python16 4 00

SqueezeAILab/LLMCompiler
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
Language:Python1.5k 25 7111
SqueezeAILab/SqueezeLLM
[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
Language:Python651 18 2743
SqueezeAILab/TinyAgent
[EMNLP 2024 Demo] TinyAgent: Function Calling at the Edge!
Language:Python313 10 651
SqueezeAILab/KVQuant
[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
Language:Python307 13 1526
SqueezeAILab/LLM2LLM
[ACL 2024] LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement
Language:Python155 6 610
SqueezeAILab/open_source_projects
Open Source Projects from Pallas Lab
20 3 02
SqueezeAILab/Tool2Vec
Efficient and Scalable Estimation of Tool Representations in Vector Space
Language:Python16 4 00