BlinkDL / RWKV-CUDALinks
The CUDA version of the RWKV language model ( https://github.com/BlinkDL/RWKV-LM )
☆223Updated 9 months ago
Alternatives and similar repositories for RWKV-CUDA
Users that are interested in RWKV-CUDA are comparing it to the libraries listed below
Sorting:
- GPTQ inference Triton kernel☆307Updated 2 years ago
- Reorder-based post-training quantization for large language model☆195Updated 2 years ago
- ☆159Updated 2 years ago
- ☆154Updated 2 years ago
- The official implementation of the EMNLP 2023 paper LLM-FP4☆214Updated last year
- 🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.☆217Updated last month
- Standalone Flash Attention v2 kernel without libtorch dependency☆110Updated last year
- A collection of memory efficient attention operators implemented in the Triton language.☆278Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆265Updated 2 months ago
- Get down and dirty with FlashAttention2.0 in pytorch, plug in and play no complex CUDA kernels☆109Updated 2 years ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆114Updated last year
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆328Updated 6 months ago
- Tutorials for writing high-performance GPU operators in AI frameworks.☆131Updated 2 years ago
- ☆125Updated last year
- A model compression and acceleration toolbox based on pytorch.☆332Updated last year
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆477Updated last year
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆40Updated 6 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆139Updated last month
- ☆95Updated 5 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆119Updated 3 months ago
- LLaMa/RWKV onnx models, quantization and testcase☆365Updated 2 years ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆381Updated last year
- Implementation of "Attention Is Off By One" by Evan Miller☆197Updated 2 years ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year
- ☆128Updated 8 months ago
- ☆199Updated 4 months ago
- Implementation of FlashAttention in PyTorch☆168Updated 8 months ago
- A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.☆177Updated 5 months ago
- ☆96Updated 4 months ago
- This repository contains integer operators on GPUs for PyTorch.☆216Updated last year