The CUDA version of the RWKV language model ( https://github.com/BlinkDL/RWKV-LM )
☆234Dec 10, 2025Updated 11 months ago
Alternatives and similar repositories for RWKV-CUDA
Users that are interested in RWKV-CUDA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- RWKV-7 7.2B fp16 15000+ tps decoding @ single 5090☆133Sep 10, 2026Updated 2 months ago
- ☆32May 26, 2024Updated 2 years ago
- study of cutlass☆22Nov 10, 2024Updated 2 years ago
- ☆126Dec 15, 2023Updated 2 years ago
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆481Mar 15, 2024Updated 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.
- A torchless, c++ rwkv implementation using 8bit quantization, written in cuda/hip/vulkan for maximum compatibility and minimum dependenci…☆315Jan 31, 2024Updated 2 years ago
- continous batching and parallel acceleration for RWKV6☆23Jun 28, 2024Updated 2 years ago
- ☆187Oct 22, 2026Updated 3 weeks ago
- ☆12Dec 14, 2024Updated last year
- ☆43Mar 29, 2023Updated 3 years ago
- ☆14Oct 19, 2026Updated 3 weeks ago
- [ICDCS 2023] Evaluation and Optimization of Gradient Compression for Distributed Deep Learning☆10Apr 28, 2023Updated 3 years ago
- RWKV centralised docs for the community☆37Jan 17, 2026Updated 9 months ago
- This project demonstrates the computation process of the RWKV (Receptance Weighted Key Value) model through Excel spreadsheets.☆21Jun 7, 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.
- row-major matmul optimization☆761May 14, 2026Updated 5 months ago
- INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model☆1,592Mar 23, 2025Updated last year
- RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable)…☆14,775Nov 4, 2026Updated last week
- RWKV in nanoGPT style☆199Jun 9, 2024Updated 2 years ago
- play gemm with tvm☆91Jul 22, 2023Updated 3 years ago
- HunyuanDiT with TensorRT and libtorch☆18May 22, 2024Updated 2 years ago
- JAX implementations of RWKV☆18Sep 26, 2023Updated 3 years ago
- RWKV-v2-RNN trained on the Pile. See https://github.com/BlinkDL/RWKV-LM for details.☆67Sep 14, 2022Updated 4 years ago
- ☆14May 11, 2025Updated last year
- 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.
- ☆28Feb 26, 2026Updated 8 months ago
- GoldFinch and other hybrid transformer components☆17Dec 9, 2025Updated 11 months ago
- call rwkv v4/v5/v6/v7 raven/world/finch 1B5-14B rwkv.cpp using csharp cpu/gpu (support INT4,8,Float16,32)☆36Feb 21, 2025Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆96Jun 21, 2026Updated 4 months ago
- ☆34May 20, 2026Updated 5 months ago
- A large-scale RWKV v7(World, PRWKV, Hybrid-RWKV) inference. Capable of inference by combining multiple states(Pseudo MoE). Easy to deploy…☆52Oct 21, 2025Updated last year
- Official repository Flash Local Linear Attention☆40May 28, 2026Updated 5 months ago
- Gradio UI for RWKV LLM☆27Feb 21, 2023Updated 3 years ago
- RWKV Batch infer backend ⚡Base on albatross https://github.com/BlinkDL/Albatross 🕊️☆37Jul 27, 2026Updated 3 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.
- ☆33Mar 30, 2023Updated 3 years ago
- Efficient PScan implementation in PyTorch☆17Jan 2, 2024Updated 2 years ago
- A tool convert TensorRT engine/plan to a fake onnx☆41Nov 22, 2022Updated 3 years ago
- A go wrapper around the rwkv.cpp library☆20Mar 4, 2024Updated 2 years ago
- PyTorch bindings for CUTLASS grouped GEMM.☆157May 29, 2025Updated last year
- A simple high performance CUDA GEMM implementation.☆440Jan 4, 2024Updated 2 years ago
- Framework agnostic python runtime for RWKV models☆147Aug 24, 2023Updated 3 years ago
Are these results useful?