Oneflow-Inc / conda-env
☆12Updated last year
Related projects ⓘ
Alternatives and complementary repositories for conda-env
- OneFlow Serving☆20Updated 9 months ago
- ☆22Updated last year
- ☆18Updated 10 months ago
- GPTQ inference TVM kernel☆35Updated 6 months ago
- OneFlow->ONNX☆42Updated last year
- ☆11Updated 9 months ago
- ☆14Updated 2 years ago
- study of cutlass☆19Updated this week
- An external memory allocator example for PyTorch.☆13Updated 3 years ago
- ☆79Updated 2 months ago
- A TVM-like CUDA/C code generator.☆9Updated 2 years ago
- ☆11Updated 3 years ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆85Updated 8 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆98Updated 2 months ago
- ☆13Updated 7 months ago
- TensorRT LLM Benchmark Configuration☆11Updated 3 months ago
- Inference framework for MoE layers based on TensorRT with Python binding☆41Updated 3 years ago
- play gemm with tvm☆84Updated last year
- My learning notes about AI, including Machine Learning and Deep Learning.☆18Updated 5 years ago
- Summary of system papers/frameworks/codes/tools on training or serving large model☆56Updated 10 months ago
- This is a demo how to write a high performance convolution run on apple silicon☆52Updated 2 years ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆52Updated 3 months ago
- A toolkit for developers to simplify the transformation of nn.Module instances. It's now corresponding to Pytorch.fx.☆13Updated last year
- ☆55Updated 5 months ago
- 分层解耦的深度学习推理引擎☆60Updated 2 months ago
- Quantized Attention on GPU☆29Updated last week
- TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.☆151Updated this week
- Benchmark code for the "Online normalizer calculation for softmax" paper☆59Updated 6 years ago
- Distributed DataLoader For Pytorch Based On Ray☆24Updated 3 years ago