daquexian / faster-rwkvLinks
☆123Updated last year
Alternatives and similar repositories for faster-rwkv
Users that are interested in faster-rwkv are comparing it to the libraries listed below
Sorting:
- Inference RWKV v5, v6 and v7 with Qualcomm AI Engine Direct SDK☆67Updated last week
- Inference RWKV with multiple supported backends.☆47Updated this week
- A converter for llama2.c legacy models to ncnn models.☆87Updated last year
- ☆83Updated 2 years ago
- llm deploy project based onnx.☆37Updated 7 months ago
- stable diffusion using mnn☆68Updated last year
- simplify >2GB large onnx model☆57Updated 6 months ago
- qwen2 and llama3 cpp implementation☆44Updated 11 months ago
- ☆32Updated 10 months ago
- NVIDIA TensorRT Hackathon 2023复赛选题:通义千问Qwen-7B用TensorRT-LLM模型搭建及优化☆42Updated last year
- Standalone Flash Attention v2 kernel without libtorch dependency☆109Updated 8 months ago
- ☆36Updated 7 months ago
- A Toolkit to Help Optimize Large Onnx Model☆158Updated last year
- ☆74Updated 6 months ago
- ☆127Updated 5 months ago
- ☆58Updated 6 months ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆37Updated 3 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆124Updated last month
- Large Language Model Onnx Inference Framework☆35Updated 4 months ago
- ☆138Updated last year
- Inference TinyLlama models on ncnn☆24Updated last year
- ☆71Updated 2 years ago
- 将MNN拆解的简易前向推理框架(for study!)☆22Updated 4 years ago
- NeRF in NCNN with c++ & vulkan☆67Updated last year
- 📚FFPA(Split-D): Extend FlashAttention with Split-D for large headdim, O(1) GPU SRAM complexity, 1.8x~3x↑🎉 faster than SDPA EA.☆183Updated 3 weeks ago
- 使用 CUDA C++ 实现的 llama 模型推理框架☆57Updated 6 months ago
- ☆66Updated 2 years ago
- Serving Inside Pytorch☆160Updated 3 weeks ago
- libvits-ncnn is an ncnn implementation of the VITS library that enables cross-platform GPU-accelerated speech synthesis.🎙️💻☆60Updated 2 years ago
- symmetric int8 gemm☆66Updated 4 years ago