ruipeterpan / specreasonLinks
PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]
☆42Updated 3 weeks ago
Alternatives and similar repositories for specreason
Users that are interested in specreason are comparing it to the libraries listed below
Sorting:
- ☆43Updated 8 months ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆52Updated 5 months ago
- [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling☆36Updated 2 weeks ago
- ☆113Updated last month
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆87Updated last month
- ☆35Updated 2 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆29Updated 5 months ago
- Source code for the paper "LongGenBench: Long-context Generation Benchmark"☆22Updated 9 months ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆61Updated 3 weeks ago
- ☆54Updated 8 months ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆49Updated 9 months ago
- ☆20Updated 8 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆38Updated 11 months ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆42Updated last year
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆88Updated last month
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆124Updated 2 months ago
- ☆268Updated 3 weeks ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆140Updated 2 weeks ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆101Updated 3 months ago
- Multi-Candidate Speculative Decoding☆36Updated last year
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆128Updated 5 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆198Updated 5 months ago
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆81Updated 5 months ago
- ☆24Updated 2 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆48Updated 9 months ago
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆23Updated 9 months ago
- ☆25Updated 5 months ago
- TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆171Updated last month
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆95Updated last year
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆50Updated 8 months ago