🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation feedback, cross-platform NVIDIA/AMD, Kernelbook + KernelBench
☆136Nov 10, 2025Updated 6 months ago
Alternatives and similar repositories for TritonForge
Users that are interested in TritonForge are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆57Oct 11, 2025Updated 7 months ago
- ☆58Mar 31, 2026Updated last month
- ☆28Jul 29, 2025Updated 9 months ago
- ☆81Sep 15, 2025Updated 8 months ago
- [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning☆69Oct 31, 2025Updated 6 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- [ICLR 2025] DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference☆51Jun 17, 2025Updated 11 months ago
- ☆19Jun 3, 2023Updated 2 years ago
- OpenAI gym environments for goal-conditioned and language-conditioned reinforcement learning☆14Jan 27, 2026Updated 3 months ago
- Estimate MFU for DeepSeekV3☆26Jan 5, 2025Updated last year
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆211Updated this week
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆300Nov 7, 2025Updated 6 months ago
- An agent for CUDA compute-communication kernel co-design☆34May 7, 2026Updated 2 weeks ago
- Moatless Testbeds allows you to create isolated testbed environments in a Kubernetes cluster where you can apply code changes through git…☆14Apr 9, 2025Updated last year
- Tile-based language built for AI computation across all scales☆153Updated this week
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆168Feb 27, 2026Updated 2 months ago
- ☆37Feb 12, 2025Updated last year
- PaperHelper: Knowledge-Based LLM QA Paper Reading Assistant with Reliable References☆21Jun 13, 2024Updated last year
- Collection of kernels written in Triton language☆194Jan 27, 2026Updated 3 months ago
- ☆14Jul 13, 2025Updated 10 months ago
- ☆52May 19, 2025Updated last year
- slime is an LLM post-training framework for RL Scaling.☆5,710Updated this week
- A Dual-RL method DVL: Dual-V Learning for offline and online reinforcement learning☆16Oct 22, 2023Updated 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.
- DeeperGEMM: crazy optimized version☆86May 5, 2025Updated last year
- Materials for learning SGLang☆821Jan 5, 2026Updated 4 months ago
- a fully learned index for larger-than-memory databases☆15Sep 17, 2022Updated 3 years ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆263Aug 9, 2025Updated 9 months ago
- Reproducing R1 for Code with Reliable Rewards☆309May 5, 2025Updated last year
- Utility scripts for PyTorch (e.g. Make Perfetto show some disappearing kernels, Memory profiler that understands more low-level allocatio…☆107Sep 11, 2025Updated 8 months ago
- AMD RAD's multi-GPU Triton-based framework for seamless multi-GPU programming☆188Updated this week
- ☆22May 5, 2025Updated last year
- Flash-Linear-Attention models beyond language☆21Aug 28, 2025Updated 8 months 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.
- Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.☆66Mar 17, 2026Updated 2 months ago
- A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.☆106Dec 17, 2025Updated 5 months ago
- Fast, memory-efficient attention column reduction (e.g., sum, mean, max)☆46Feb 10, 2026Updated 3 months ago
- My learning notes for ML SYS.☆6,354Updated this week
- Drop-in environment replacements that make your RL algorithm train faster.☆22Jun 19, 2024Updated last year
- Implementation from scratch in C of the Multi-head latent attention used in the Deepseek-v3 technical paper.☆18Jan 15, 2025Updated last year
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆995Feb 25, 2026Updated 2 months ago