Oneflow-Inc / servingLinks
OneFlow Serving
☆20Updated 6 months ago
Alternatives and similar repositories for serving
Users that are interested in serving are comparing it to the libraries listed below
Sorting:
- ☆18Updated last year
- ☆16Updated last year
- ☆23Updated 2 years ago
- OneFlow->ONNX☆43Updated 2 years ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆121Updated 5 months ago
- ☆33Updated 8 months ago
- A toolkit for developers to simplify the transformation of nn.Module instances. It's now corresponding to Pytorch.fx.☆13Updated 2 years ago
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆20Updated 2 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆112Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆16Updated last year
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆41Updated 8 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆78Updated last year
- A CUDA kernel for NHWC GroupNorm for PyTorch☆21Updated 11 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆45Updated 4 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆94Updated last month
- A Triton JIT runtime and ffi provider in C++☆27Updated this week
- ☆100Updated last year
- ☆12Updated 2 years ago
- GPTQ inference TVM kernel☆39Updated last year
- ☆97Updated 7 months ago
- study of cutlass☆22Updated 11 months ago
- ☆101Updated 5 months ago
- Transformer related optimization, including BERT, GPT☆17Updated 2 years ago
- ☆129Updated 10 months ago
- Quantized Attention on GPU☆44Updated 11 months ago
- ☆11Updated 4 years ago
- This is a demo how to write a high performance convolution run on apple silicon☆56Updated 3 years ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆76Updated last year
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆50Updated last year
- ☆18Updated 2 weeks ago