π° Must-read papers and blogs on Speculative Decoding β‘οΈ
β1,309Jun 27, 2026Updated 4 months ago
Alternatives and similar repositories for SpeculativeDecodingPapers
Users that are interested in SpeculativeDecodingPapers are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)β415Apr 22, 2025Updated last year
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).β2,579Feb 20, 2026Updated 8 months ago
- Fast inference from large lauguage models via speculative decodingβ925Aug 22, 2024Updated 2 years ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Lengthβ175Dec 23, 2025Updated 10 months ago
- Explorations into some recent techniques surrounding speculative decodingβ308Dec 22, 2024Updated last year
- GPU virtual machines on DigitalOcean Gradient AI β’ AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Accelerationβ70Feb 21, 2025Updated last year
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**β231Feb 13, 2025Updated last year
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.β1,289Updated this week
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Headsβ2,776Jun 25, 2024Updated 2 years ago
- Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.β227Mar 18, 2026Updated 8 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decodingβ1,346Mar 6, 2025Updated last year
- π° Must-read papers on KV Cache Compression (constantly updating π€).β751Aug 16, 2026Updated 3 months ago
- Multi-Candidate Speculative Decodingβ41Apr 22, 2024Updated 2 years ago
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decodingβ280Aug 31, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer β’ AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- πA curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.πβ5,565Oct 20, 2026Updated 3 weeks ago
- A curated list for Efficient Large Language Modelsβ2,052Jun 17, 2025Updated last year
- [ACL 2026 (Main)] LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verificationβ86Jul 14, 2025Updated last year
- REST: Retrieval-Based Speculative Decoding, NAACL 2024β221Mar 5, 2026Updated 8 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)β117Mar 20, 2025Updated last year
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)β56Mar 14, 2025Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decodingβ162Dec 4, 2024Updated last year
- Codes for our paper "Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation" (EMNLP 2023 Findings)β47Dec 9, 2023Updated 2 years ago
- scalable and robust tree-based speculative decoding algorithmβ376Jan 28, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits β’ AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- β68Dec 3, 2024Updated last year
- Reading notes on Speculative Decoding papersβ50Jun 2, 2026Updated 5 months ago
- Awesome LLM compression research papers and tools.β1,898Updated this week
- Paper list for Efficient Reasoning.β910May 29, 2026Updated 5 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automatonβ53May 12, 2026Updated 6 months ago
- This repository is the official implementation of "Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE" [ACL 2026 Maiβ¦β39Oct 5, 2025Updated last year
- [EMNLP2026 Main] Official implementation of βDomino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decodingβ.β141Jul 25, 2026Updated 3 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitinβ¦β74Jun 26, 2024Updated 2 years ago
- FlashInfer: Kernel Library for LLM Servingβ6,958Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer β’ AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Trainingβ1,901Updated this week
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafterβ187Feb 27, 2026Updated 8 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Seβ¦β869Mar 6, 2025Updated last year
- β33May 24, 2025Updated last year
- Awesome-LLM-KV-Cache: A curated list of πAwesome LLM KV Cache Papers with Codes.β474Jun 17, 2026Updated 5 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"β1,116May 30, 2026Updated 5 months ago
- My learning notes for ML SYS.β7,684Oct 21, 2026Updated 3 weeks ago
Are these results useful?