uservan / speculative_thinkingLinks
☆20Updated 3 weeks ago
Alternatives and similar repositories for speculative_thinking
Users that are interested in speculative_thinking are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆45Updated 7 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆46Updated 8 months ago
- ☆104Updated 2 weeks ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆28Updated 4 months ago
- ☆16Updated this week
- Code for the EMNLP24 paper "A simple and effective L2 norm based method for KV Cache compression."☆12Updated 6 months ago
- Codebase for Instruction Following without Instruction Tuning☆34Updated 9 months ago
- ☆42Updated 7 months ago
- The official implementation for Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free☆44Updated last month
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning☆99Updated last month
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆39Updated 2 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]☆39Updated last month
- [NAACL 2025] A Closer Look into Mixture-of-Experts in Large Language Models☆52Updated 4 months ago
- The rule-based evaluation subset and code implementation of Omni-MATH☆22Updated 6 months ago
- ☆51Updated 3 months ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆47Updated 7 months ago
- More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression☆11Updated 5 months ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆54Updated 3 months ago
- ☆30Updated last month
- ☆22Updated 11 months ago
- Repo for ACL2023 Findings paper "Emergent Modularity in Pre-trained Transformers"☆25Updated 2 years ago
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆39Updated last year
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆51Updated 4 months ago
- The official implementation of "LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation"☆20Updated 2 months ago
- ☆37Updated 9 months ago
- Long Context Extension and Generalization in LLMs☆57Updated 9 months ago
- ☆16Updated 2 months ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆79Updated 5 months ago
- Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"☆88Updated last month
- Inference Code for Paper "Harder Tasks Need More Experts: Dynamic Routing in MoE Models"☆52Updated 10 months ago