☆87Nov 11, 2026Updated this week
Alternatives and similar repositories for verl-SpeCo
Users that are interested in verl-SpeCo are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆11Oct 29, 2026Updated last week
- [EMNLP2026 Main] Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆141Jul 25, 2026Updated 3 months ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆187Feb 27, 2026Updated 8 months ago
- ☆27Feb 27, 2026Updated 8 months ago
- ⚡ Official code for “ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models…☆17Oct 15, 2026Updated 3 weeks ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- verl Ascend specific recipe☆23Updated this week
- Fast and memory-efficient exact attention☆23Updated this week
- The official repo of "Draft-OPD: On-Policy Distillation for Speculative Draft Models"☆84Sep 4, 2026Updated 2 months ago
- A scalable serving system for building and running modular diffusion workflows across GPU clusters.☆12Sep 23, 2026Updated last month
- InfiniCCL is a unified, cross-platform collective communication library designed for heterogeneous accelerator environments.☆21Updated this week
- A PyTorch native library for training speculative decoding models☆267Updated this week
- BlitzScale Router - Distributed LLM Inference Router (Rust)☆18May 25, 2026Updated 5 months ago
- Ongoing research training transformer models at scale☆13Updated this week
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆952Updated this week
- 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.
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,280Updated this week
- dUltra: Ultra-Fast Diffusion Large Language Models via Reinforcement Learning☆18Jul 11, 2026Updated 4 months ago
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆23Nov 28, 2025Updated 11 months ago
- SpecOPD: Branch-parallel on-policy distillation for faster speculative decoding.☆27Updated this week
- ☆19May 27, 2026Updated 5 months ago
- ☆17Jan 31, 2026Updated 9 months ago
- Awesome-Parallel-Speculative-Decoding☆21Oct 17, 2026Updated 3 weeks ago
- W4A16 MoE GEMM CUDA kernel. Tuned for H200, B200 & B300.☆14Oct 30, 2026Updated last week
- ☆45Jun 23, 2026Updated 4 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- FA4-based Relative Attention Kernel developed by TML and Colfax☆18Sep 11, 2026Updated 2 months ago
- Miles-diffusion is an post-training framework for large-scale diffusion model training and production workloads, forked from and co-evolv…☆119Updated this week
- verl Zero-Mismatch Dense/MoE HuggingFace Rollout☆77Updated this week
- Official implementation of "Learning To Draft: Adaptive Speculative Decoding with Reinforcement Learning" (ICLR 2026)☆24Mar 1, 2026Updated 8 months ago
- ☆124Updated this week
- High-performance RL post-training infrastructure. Designed to achieve bitwise operator-level train-inference consistency across heterogen…☆459Updated this week
- ☆12Aug 1, 2026Updated 3 months ago
- [ICML 2026] Residual Context Diffusion (RCD): Repurposing discarded signals as structured priors for high-performance reasoning in dLLMs.☆62Jun 28, 2026Updated 4 months ago
- Muon in Int8 Precision Made Possible☆21Updated this week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Code for the paper *Attention Drift: What Speculative Decoding Models Learn*.☆33May 12, 2026Updated 5 months ago
- The code for paper "FloE: On-the-Fly MoE Inference on Memory-constrained GPU“.☆12Apr 1, 2025Updated last year
- Twinkle✨: Training workbench to make your model glow.☆264Updated this week
- dInfer: An Efficient Inference Framework for Diffusion Language Models☆491Updated this week
- Some funny cute/cuteDSL code snippets☆35Mar 2, 2026Updated 8 months ago
- The repository for ATC'25 paper "Greyhound: Hunting Fail-Slows in Hybrid-Parallel Training at Scale"☆19Sep 7, 2026Updated 2 months ago
- Flash-Flash KDA: H100-optimized Flash Kimi Delta Attention kernels☆24Jul 24, 2026Updated 3 months ago
Are these results useful?