Oneflow-Inc / servingLinks
OneFlow Serving
☆20Updated 2 months ago
Alternatives and similar repositories for serving
Users that are interested in serving are comparing it to the libraries listed below
Sorting:
- 🤗CacheDiT: A Training-free and Easy-to-use Cache Acceleration Toolbox for Diffusion Transformers🔥☆61Updated this week
- OneFlow->ONNX☆43Updated 2 years ago
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆18Updated 8 months ago
- ☆16Updated last year
- ☆23Updated 2 years ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆38Updated last week
- ☆18Updated last year
- ☆29Updated 4 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆80Updated last month
- A toolkit for developers to simplify the transformation of nn.Module instances. It's now corresponding to Pytorch.fx.☆13Updated 2 years ago
- Odysseus: Playground of LLM Sequence Parallelism☆70Updated last year
- study of cutlass☆21Updated 7 months ago
- Transformer related optimization, including BERT, GPT☆17Updated last year
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆38Updated 3 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆16Updated last year
- GPTQ inference TVM kernel☆40Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆92Updated 3 weeks ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆100Updated last year
- ☆96Updated 9 months ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆71Updated 10 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆110Updated 9 months ago
- ☆11Updated 3 months ago
- ☆14Updated 10 months ago
- A CUDA kernel for NHWC GroupNorm for PyTorch☆19Updated 7 months ago
- ☆12Updated 2 years ago
- CVFusion is an open-source deep learning compiler to fuse the OpenCV operators.☆29Updated 2 years ago
- ☆60Updated last month
- ☆11Updated last year
- Quantized Attention on GPU☆44Updated 7 months ago
- A practical way of learning Swizzle☆20Updated 4 months ago