abdelfattah-lab / nitro
Lightweight Python Wrapper for OpenVINO, enabling LLM inference on NPUs
☆14Updated 4 months ago
Alternatives and similar repositories for nitro:
Users that are interested in nitro are comparing it to the libraries listed below
- ☆55Updated 2 weeks ago
- ☆31Updated this week
- Quantized Attention on GPU☆45Updated 5 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆65Updated last week
- ☆19Updated 6 months ago
- Open deep learning compiler stack for cpu, gpu and specialized accelerators☆18Updated this week
- FractalTensor is a programming framework that introduces a novel approach to organizing data in deep neural networks (DNNs) as a list of …☆26Updated 4 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆82Updated last week
- ☆68Updated last month
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆45Updated 9 months ago
- ☆26Updated last year
- ☆67Updated this week
- ☆29Updated this week
- ☆28Updated 2 months ago
- Debug print operator for cudagraph debugging☆10Updated 8 months ago
- DeeperGEMM: crazy optimized version☆67Updated 3 weeks ago
- Benchmark tests supporting the TiledCUDA library.☆16Updated 5 months ago
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆15Updated this week
- Odysseus: Playground of LLM Sequence Parallelism☆68Updated 10 months ago
- ☆78Updated 5 months ago
- GPTQ inference TVM kernel☆38Updated last year
- Benchmark PyTorch Custom Operators☆14Updated last year
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆33Updated last month
- ☆30Updated last year
- An external memory allocator example for PyTorch.☆14Updated 3 years ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆36Updated 3 weeks ago
- TensorRT LLM Benchmark Configuration☆13Updated 9 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆116Updated this week
- Explore training for quantized models☆17Updated 3 months ago
- ☆13Updated last month