Bitwise-identical token probabilities between RL rollout (vLLM) and training
☆38Nov 8, 2026Updated this week
Alternatives and similar repositories for zero-mismatch-rl
Users that are interested in zero-mismatch-rl are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆32Updated this week
- Parallel Constraint Decoding using Java and Llama.cpp compared to Python 🔥☆15Sep 29, 2026Updated last month
- windows桌面时钟☆10Mar 23, 2021Updated 5 years ago
- ☆11Sep 5, 2025Updated last year
- An implement of guandan game, known as 掼蛋.☆10Jan 7, 2026Updated 10 months ago
- 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.
- GC MoE is a CuTe DSL implementation of FP8/FP4 mixture-of-experts inference with CUDA Green Contexts for NVIDIA Hopper and Blackwell GPUs…☆25Updated this week
- Compact, expandable tool rows for Pi in its own compact style or Claude Code's, with a silent mode and a GitHub Dark theme.☆19Nov 4, 2026Updated last week
- Minimal NextJS 16 starter project with biome, shadcn, tailwind v4, ts env and more☆10Updated this week
- [ICML 2022 Spotlight] Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks☆11May 21, 2023Updated 3 years ago
- Marco Ciampini's portfolio☆11May 11, 2024Updated 2 years ago
- official code for Dynamic Smooth Label Assignment☆12Oct 5, 2022Updated 4 years ago
- OKX Dex-Widget Configurator Sample☆17Jan 15, 2026Updated 9 months ago
- plan☆11Aug 17, 2019Updated 7 years ago
- ☆14Aug 14, 2026Updated 2 months 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.
- Reproduction of the paper "Soft Q-Learning with Mutual Information Regularization" CoRL 2019.☆10Jan 10, 2019Updated 7 years ago
- ☆12Mar 23, 2018Updated 8 years ago
- ☆13Jun 24, 2026Updated 4 months ago
- Code for abstracting, evaluating, and visualizing Markov Decision Processes.☆11Jan 12, 2017Updated 9 years ago
- (TG'2023) Official code for the paper "Revisiting of AlphaStar" (previously called "Rethinking of AlphaStar"). It compares the raw interf…☆10Sep 6, 2021Updated 5 years ago
- Solana name service resolver in browser☆16Jan 28, 2026Updated 9 months ago
- Software Engineering Agents for Inspect AI☆41Updated this week
- Learning bisimulation metrics for control, particularly suited to sparse reward settings☆11Feb 28, 2023Updated 3 years ago
- External agents for the Dogecoin <-> Ethereum bridge☆10Jun 14, 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.
- ☆14Apr 11, 2022Updated 4 years ago
- MCP server that connects Claude to local Ollama models, delegating simple tasks to save tokens for complex reasoning☆16Oct 23, 2026Updated 2 weeks ago
- CLI that benchmarks AI coding agents on OpenCode and shows where the tokens go☆14Oct 16, 2026Updated 3 weeks ago
- Using reinforcement learning algorithm for multi-agent target assignment☆13Aug 9, 2022Updated 4 years ago
- Implementation of paper Deep Back Projection Network paper☆10Jul 23, 2018Updated 8 years ago
- The Official PyTorch implementation of "Part Aware Contrastive Learning for Self-Supervised Action Recognition" in IJCAI 2023☆13Nov 9, 2023Updated 3 years ago
- DEFT: Decompositional Efficient Fine-Tuning for Text-to-Image Models (NeuralPS 2025)☆11Updated this week
- A Curated Collection of Frontier Language Model Architectures☆14Jan 30, 2026Updated 9 months ago
- Deep Learning StarCraft II AI☆14Nov 4, 2026Updated last week
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Responsive Solana wallet authentication and account modal built on top of @solana/web3.js with NextAuth integration and shadcn/ui☆15Nov 25, 2024Updated last year
- Track all trades on uniswap v2 in your telegram bot in real time.☆11Nov 13, 2021Updated 4 years ago
- Code for Transformers are Adaptable Task Planners, CoRL 2022☆12Mar 28, 2023Updated 3 years ago
- Dist-MoE implements Speed-of-Light distributed Mixture-of-Experts forward and backward kernels. They are highly optimized and fused comm-…☆73Oct 29, 2026Updated last week
- Parameter-efficient fine-tuning of LLMs using QLoRA — 4-bit quantization, PEFT adapters, W&B experiment tracking☆14Oct 13, 2026Updated 3 weeks ago
- NCU-driven iterative optimization workflow for CUDA/CUTLASS/Triton/CuTe DSL kernels.☆25Apr 10, 2026Updated 7 months ago
- AISTATS 2019: Reference-based Adversarial Sampling & Its applications to Soft Q-learning☆15Jan 21, 2019Updated 7 years ago
Are these results useful?