SqueezeAILab

All

15 repositories

MultipoleAttention
Public
[NeurIPS 2025] Multipole Attention for Efficient Long Context Reasoning
Python
•0•15•2•0•Updated Dec 5, 2025Dec 5, 2025
CDLM
Public
CDLM: Consistency Diffusion Language Models for Faster Sampling
Python
•
MIT License
•0•11•0•0•Updated Nov 25, 2025Nov 25, 2025
plan-and-act
Public
[ICML 2025] Improving Planning of Agents for Long-Horizon Tasks
Python
•
MIT License
•0•15•0•0•Updated Oct 2, 2025Oct 2, 2025
sciml-agent
Public
SciMLAgents: Write the Solver, Not the Solution
benchmark ode scientific-computing evaluation-framework sciml large-language-model llm-agent
MIT License
•0•4•0•0•Updated Sep 15, 2025Sep 15, 2025
reward-under-attack
Public
0•0•0•0•Updated Jul 26, 2025Jul 26, 2025
ETS
Public
ETS: Efficient Tree Search for Inference-Time Scaling
Python
•1•9•1•0•Updated Feb 28, 2025Feb 28, 2025
QuantSpec
Public
0•6•2•0•Updated Feb 22, 2025Feb 22, 2025
SqueezedAttention
Public
[ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference
Python
•8•54•4•0•Updated Nov 20, 2024Nov 20, 2024
Tool2Vec
Public
Efficient and Scalable Estimation of Tool Representations in Vector Space
nlp natural-language-processing tool transformer bert llm deberta-v3 function-calling tool-learning
Python
•
MIT License
•4•29•2•0•Updated Sep 5, 2024Sep 5, 2024
TinyAgent
Public
[EMNLP 2024 Demo] TinyAgent: Function Calling at the Edge!
Python
•
MIT License
•71•461•7•1•Updated Sep 4, 2024Sep 4, 2024
KVQuant
Public
[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
natural-language-processing compression text-generation transformer llama quantization mistral model-compression efficient-inference efficient-model
Python
•38•393•16•1•Updated Aug 13, 2024Aug 13, 2024
SqueezeLLM
Public
[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
natural-language-processing text-generation transformer llama quantization model-compression efficient-inference post-training-quantization large-language-models llm
Python
•
MIT License
•48•710•16•4•Updated Aug 13, 2024Aug 13, 2024
LLMCompiler
Public
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
nlp natural-language-processing transformer llama efficient-inference large-language-models llm llms llm-agent function-calling
Python
•
MIT License
•123•1.8k•4•2•Updated Jul 10, 2024Jul 10, 2024
LLM2LLM
Public
[ACL 2024] LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement
nlp natural-language-processing transformer llama data-augmentation synthetic-dataset-generation llm llms llama2
Python
•
MIT License
•16•191•2•0•Updated Mar 25, 2024Mar 25, 2024
open_source_projects
Public
Open Source Projects from Pallas Lab
MIT License
•2•21•0•0•Updated Oct 10, 2021Oct 10, 2021