PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation (ICLR 26)
☆34Jun 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:
- Official Implementation of DART (DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference).☆66Feb 8, 2026Updated 5 months ago
- Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆127Jul 25, 2026Updated last week
- Official implementation for "K-Forcing: Joint Next-K-Token Decoding via Push-Forward Language Modeling"☆18Jun 14, 2026Updated last month
- A selective knowledge distillation algorithm for efficient speculative decoders☆39Nov 27, 2025Updated 8 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆403Apr 22, 2025Updated last year
- 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.
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,049Updated this week
- Source code to accompany research paper on training multi token prediction language models using self-distillation.☆39Feb 21, 2026Updated 5 months ago
- Official implementation of "Learning To Draft: Adaptive Speculative Decoding with Reinforcement Learning" (ICLR 2026)☆22Mar 1, 2026Updated 5 months ago
- ☆33Updated this week
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆171Dec 23, 2025Updated 7 months ago
- Recovery-Bench is a benchmark for evaluating the capability of LLM agents to recover from mistakes☆27Jun 17, 2026Updated last month
- Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.☆214Mar 18, 2026Updated 4 months ago
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆695Updated this week
- ☆20May 14, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆391Apr 16, 2026Updated 3 months ago
- Keyformer proposes KV Cache reduction through key tokens identification and without the need for fine-tuning☆58Mar 26, 2024Updated 2 years ago
- AFPQ code implementation☆23Nov 6, 2023Updated 2 years ago
- Codebase for the work “Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?”☆75Apr 14, 2026Updated 3 months ago
- ☆12May 19, 2022Updated 4 years ago
- ☆17Apr 7, 2025Updated last year
- [ICLR 2026] AdaBlock-dLLM: Semantic-Aware Diffusion LLM Inference via Adaptive Block Size☆15Jan 28, 2026Updated 6 months ago
- [ACL 2026 (Main)] LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆84Jul 14, 2025Updated last year
- ☆49Sep 13, 2025Updated 10 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆73May 12, 2026Updated 2 months ago
- Speculative Decoding Meets Quantization: Compatibility Evaluation and Hierarchical Framework Design☆24May 29, 2025Updated last year
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,496Feb 20, 2026Updated 5 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆75Oct 2, 2025Updated 10 months ago
- The official repo for “Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem” [EMNLP25]☆33Sep 1, 2025Updated 11 months ago
- ☆38Jun 23, 2026Updated last month
- Post-Trained MoE Can Skip Half Experts via Self-Distillation☆38May 19, 2026Updated 2 months ago
- ☆38Jul 21, 2025Updated last year
- [ICCV-2023] EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization☆29Dec 6, 2023Updated 2 years ago
- 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.
- code for the paper "A Statistical Framework for Low-bitwidth Training of Deep Neural Networks"☆29Oct 31, 2020Updated 5 years ago
- [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference☆326Jul 1, 2026Updated last month
- The official implemention of "Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration" (ICML 2026)☆24Feb 4, 2026Updated 6 months ago
- ☆62Jul 3, 2026Updated last month
- ☆48Nov 1, 2025Updated 9 months ago
- A lightweight inference engine supporting speculative speculative decoding (SSD).☆982May 10, 2026Updated 2 months ago
- Accurate and fast KV cache compression with a gating mechanism☆28Jul 27, 2026Updated last week