Reading notes on Speculative Decoding papers
☆48Jun 2, 2026Updated 4 months ago
Alternatives and similar repositories for Awesome-Speculative-Decoding
Users that are interested in Awesome-Speculative-Decoding are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,299Jun 27, 2026Updated 3 months ago
- A set of learned index papers w/o notes☆18Apr 25, 2024Updated 2 years ago
- Persistent Memory Tool Box☆12Mar 4, 2024Updated 2 years ago
- ☆14Apr 8, 2023Updated 3 years ago
- STREAMer: Benchmarking remote volatile and non-volatile memory bandwidth☆18Aug 21, 2023Updated 3 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆14May 21, 2024Updated 2 years ago
- a fully learned index for larger-than-memory databases☆15Sep 17, 2022Updated 4 years ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆746Aug 16, 2026Updated last month
- A Distribution-driven Learned Index☆16May 18, 2023Updated 3 years ago
- Official implementation for "K-Forcing: Joint Next-K-Token Decoding via Push-Forward Language Modeling"☆19Aug 16, 2026Updated last month
- The speculative decoding for uav environment☆17Oct 18, 2025Updated 11 months ago
- [ICML 2025] RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression☆55Aug 7, 2025Updated last year
- PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation (ICLR 26)☆36Jun 10, 2026Updated 3 months ago
- ☆50Sep 13, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- [ACL 2026 (Main)] LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆86Jul 14, 2025Updated last year
- This repository serves as a comprehensive survey of LLM development, featuring numerous research papers along with their corresponding co…☆362Jul 16, 2026Updated 2 months ago
- VRAFT is a framework written in C++ that implements RAFT protocol and SEDA architecture. Based on VRAFT, distributed software can be deve…☆11Sep 24, 2024Updated 2 years ago
- ☆18Dec 9, 2025Updated 10 months ago
- ☆14Jan 4, 2025Updated last year
- Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.☆223Mar 18, 2026Updated 6 months ago
- Code for the paper *Attention Drift: What Speculative Decoding Models Learn*.☆32May 12, 2026Updated 4 months ago
- TPAMI 2025 Survey Paper☆34Mar 31, 2025Updated last year
- ☆15Jan 24, 2025Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- To help search, filter, and download papers from 'acl anthology' (https://aclanthology.org/).☆19Sep 12, 2024Updated 2 years ago
- A curated list of research papers, resources, and advancements on Diffusion Cache and related efficient diffusion model acceleration tech…☆89Jul 23, 2026Updated 2 months ago
- LITS: An Optimized Learned Index for Strings☆13Sep 30, 2026Updated last week
- Jupiter is a fast, scalable, and resource-efficient collaborative edge-AI system for generative LLM inference.☆32Jul 3, 2026Updated 3 months ago
- ☆32Mar 12, 2026Updated 6 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆75Oct 2, 2025Updated last year
- ThinK: Thinner Key Cache by Query-Driven Pruning☆30Jun 2, 2026Updated 4 months ago
- Pytorch implementation of our paper accepted by ICML 2023 -- "Bi-directional Masks for Efficient N:M Sparse Training"☆14Jun 7, 2023Updated 3 years ago
- Burstable Cloud Scheduler☆17Jun 6, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,548Feb 20, 2026Updated 7 months ago
- Paper reading and discussion notes, covering AI frameworks, distributed systems, cluster management, etc.☆75Mar 4, 2026Updated 7 months ago
- Introduce a continuous intermediate representation between "masks" and "tokens" for dLLM☆15Dec 1, 2025Updated 10 months ago
- 🎓Automatically Update LLM inference systems Papers Daily using Github Actions (Update Every 12th hours)☆12Sep 28, 2026Updated last week
- ☆18Aug 15, 2022Updated 4 years ago
- Stateful LLM Serving☆107Mar 11, 2025Updated last year
- ☆21Mar 11, 2026Updated 6 months ago