Skip to content
@SqueezeAILab

SqueezeAILab

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

Popular repositories Loading

  1. LLMCompiler LLMCompiler Public

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

    Python 1.9k 136

  2. SqueezeLLM SqueezeLLM Public

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

    Python 724 52

  3. TinyAgent TinyAgent Public

    [EMNLP 2024 Demo] TinyAgent: Function Calling at the Edge!

    Python 498 74

  4. KVQuant KVQuant Public

    [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

    Python 435 49

  5. LLM2LLM LLM2LLM Public

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

    Python 196 15

  6. SqueezedAttention SqueezedAttention Public

    [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference

    Python 58 7

Repositories

Showing 10 of 16 repositories
  • reward-under-attack Public
    SqueezeAILab/reward-under-attack's past year of commit activity
    Jupyter Notebook 5 0 1 0 Updated Jul 24, 2026
  • QuantSpec Public
    SqueezeAILab/QuantSpec's past year of commit activity
    Python 14 0 2 0 Updated Mar 20, 2026
  • Arbitrage Public

    Arbitrage: Efficient Reasoning via Advantage-Aware Speculation

    SqueezeAILab/Arbitrage's past year of commit activity
    Python 6 0 1 0 Updated Dec 10, 2025
  • MultipoleAttention Public

    [NeurIPS 2025] Multipole Attention for Efficient Long Context Reasoning

    SqueezeAILab/MultipoleAttention's past year of commit activity
    Python 26 0 2 0 Updated Dec 5, 2025
  • CDLM Public

    CDLM: Consistency Diffusion Language Models for Faster Sampling

    SqueezeAILab/CDLM's past year of commit activity
    Python 41 MIT 0 0 0 Updated Nov 25, 2025
  • plan-and-act Public

    [ICML 2025] Improving Planning of Agents for Long-Horizon Tasks

    SqueezeAILab/plan-and-act's past year of commit activity
    Python 46 MIT 5 1 0 Updated Oct 2, 2025
  • sciml-agent Public

    SciMLAgents: Write the Solver, Not the Solution

    SqueezeAILab/sciml-agent's past year of commit activity
    4 MIT 0 0 0 Updated Sep 15, 2025
  • ETS Public

    ETS: Efficient Tree Search for Inference-Time Scaling

    SqueezeAILab/ETS's past year of commit activity
    Python 11 1 1 0 Updated Feb 28, 2025
  • SqueezedAttention Public

    [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference

    SqueezeAILab/SqueezedAttention's past year of commit activity
    Python 58 7 4 0 Updated Nov 20, 2024
  • Tool2Vec Public

    Efficient and Scalable Estimation of Tool Representations in Vector Space

    SqueezeAILab/Tool2Vec's past year of commit activity
    Python 32 MIT 4 2 0 Updated Sep 5, 2024
View all repositories