PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation (ICLR 26)
☆33Jun 10, 2026Updated last month
Alternatives and similar repositories for PARD
Users that are interested in PARD are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A selective knowledge distillation algorithm for efficient speculative decoders☆39Nov 27, 2025Updated 7 months ago
- Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆118Jun 24, 2026Updated 3 weeks ago
- Official Implementation of DART (DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference).☆63Feb 8, 2026Updated 5 months ago
- Official implementation of "Learning To Draft: Adaptive Speculative Decoding with Reinforcement Learning" (ICLR 2026)☆19Mar 1, 2026Updated 4 months ago
- ☆37Jul 21, 2025Updated 11 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆614Updated this week
- ☆389Apr 16, 2026Updated 3 months ago
- Keyformer proposes KV Cache reduction through key tokens identification and without the need for fine-tuning☆57Mar 26, 2024Updated 2 years ago
- Codebase for the work “Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?”☆73Apr 14, 2026Updated 3 months ago
- ☆17Jun 9, 2026Updated last month
- AFPQ code implementation☆23Nov 6, 2023Updated 2 years ago
- An efficient and scalable attention module designed to reduce memory usage and improve inference speed in large language models. Designe…☆24Jun 25, 2025Updated last year
- ☆12May 19, 2022Updated 4 years ago
- ☆35Mar 28, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆401Apr 22, 2025Updated last year
- ☆66May 12, 2026Updated 2 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆73Oct 2, 2025Updated 9 months ago
- [TMLR] Official PyTorch implementation of paper "Efficient Quantization-aware Training with Adaptive Coreset Selection"☆38Aug 20, 2024Updated last year
- ☆38Jun 23, 2026Updated 3 weeks ago
- Official repo for "SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization"☆28Mar 24, 2026Updated 3 months ago
- Post-Trained MoE Can Skip Half Experts via Self-Distillation☆38May 19, 2026Updated last month
- Study Notes for 《AI Systems Performance Engineering》☆16Mar 12, 2026Updated 4 months ago
- Template repo for Python projects, especially those focusing on machine learning and/or deep learning.☆15Jan 14, 2026Updated 6 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- [ICCV-2023] EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization☆29Dec 6, 2023Updated 2 years ago
- code for the paper "A Statistical Framework for Low-bitwidth Training of Deep Neural Networks"☆29Oct 31, 2020Updated 5 years ago
- Generating Efficient AI-Centric Kernels☆118Updated this week
- ☆63Jul 3, 2026Updated last week
- PyTorch code for full quantization of DNN using BCGD☆14Jul 24, 2019Updated 6 years ago
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,459Feb 20, 2026Updated 4 months ago
- Accurate and fast KV cache compression with a gating mechanism☆26Apr 5, 2026Updated 3 months ago
- This is a fork of SGLang for hip-attention integration. Please refer to hip-attention for detail.☆18Mar 31, 2026Updated 3 months ago
- ☆22Aug 13, 2024Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- FPGA-based hardware acceleration for dropout-based Bayesian Neural Networks.☆28Aug 15, 2023Updated 2 years ago
- (ICCV 2023) Official implementation of Rectified Straight Through Estimator (ReSTE).☆34Sep 20, 2024Updated last year
- Ring-V2 is a reasoning MoE LLM provided and open-sourced by InclusionAI.☆98Oct 23, 2025Updated 8 months ago
- Code of EMNLP 2025 paper 'UltraIF: Advancing Instruction Following from the Wild'.☆21Apr 3, 2025Updated last year
- source code of the paper: Robust Quantization: One Model to Rule Them All☆42Mar 24, 2023Updated 3 years ago
- Tries to UI development. Clone of https://www.perplexity.ai/☆11Sep 30, 2023Updated 2 years ago
- The official implementation of the ICML 2023 paper OFQ-ViT☆39Oct 3, 2023Updated 2 years ago