KaiLv69 / DuoDecoding
DuoDecoding: Hardware-aware Heterogeneous Speculative Decoding with Dynamic Multi-Sequence Drafting
☆12Updated last month
Alternatives and similar repositories for DuoDecoding:
Users that are interested in DuoDecoding are comparing it to the libraries listed below
- Multi-Candidate Speculative Decoding☆35Updated last year
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆47Updated 2 months ago
- ☆39Updated 5 months ago
- TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆133Updated last month
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆72Updated 3 months ago
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆65Updated 2 months ago
- Chain of Thoughts (CoT) is so hot! so long! We need short reasoning process!☆49Updated 3 weeks ago
- This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.☆72Updated this week
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆42Updated 5 months ago
- a survey of long-context LLMs from four perspectives, architecture, infrastructure, training, and evaluation☆46Updated 3 weeks ago
- ☆76Updated last week
- ☆15Updated 2 months ago
- ☆18Updated 4 months ago
- official code for GliDe with a CaPE☆18Updated 8 months ago
- More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression☆11Updated 3 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆77Updated last week
- ☆22Updated last month
- Unofficial implementations of block/layer-wise pruning methods for LLMs.☆68Updated 11 months ago
- ☆22Updated 3 weeks ago
- Model merging is a highly efficient approach for long-to-short reasoning.☆42Updated 3 weeks ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆183Updated 2 months ago
- LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation☆23Updated 3 weeks ago
- FR-Spec: Frequency-Ranked Speculative Sampling☆17Updated last month
- Code for "Retaining Key Information under High Compression Rates: Query-Guided Compressor for LLMs" (ACL 2024)☆17Updated 10 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]☆31Updated last week
- 🚀 LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training☆81Updated 4 months ago
- [Preprint] An inference-time decoding strategy with adaptive foresight sampling☆90Updated this week
- ☆12Updated 6 months ago
- LongSpec: Long-Context Speculative Decoding with Efficient Drafting and Verification☆50Updated last month
- ☆74Updated this week