sgl-project / tensorrt-demoLinks
TensorRT LLM Benchmark Configuration
☆13Updated last year
Alternatives and similar repositories for tensorrt-demo
Users that are interested in tensorrt-demo are comparing it to the libraries listed below
Sorting:
- Open deep learning compiler stack for cpu, gpu and specialized accelerators☆19Updated this week
- GPTQ inference TVM kernel☆39Updated last year
- Benchmark tests supporting the TiledCUDA library.☆17Updated 11 months ago
- ☆50Updated 5 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆84Updated last month
- Quantized Attention on GPU☆44Updated 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
- ☆12Updated 9 months ago
- ☆65Updated 6 months ago
- A Triton JIT runtime and ffi provider in C++☆27Updated this week
- DeeperGEMM: crazy optimized version☆72Updated 5 months ago
- ☆101Updated 5 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆78Updated last year
- Summary of system papers/frameworks/codes/tools on training or serving large model☆57Updated last year
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆46Updated 3 months ago
- DLBlas: clean and efficient kernels☆22Updated last week
- ☆53Updated last week
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆100Updated 3 months ago
- A simple calculation for LLM MFU.☆48Updated last month
- ☆19Updated last year
- 方便扩展的Cuda算子理解和优化框架,仅用在学习使用☆18Updated last year
- ☆72Updated 7 months ago
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆21Updated this week
- ☆39Updated 2 months ago
- ☆33Updated 8 months ago
- ☆78Updated 6 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆112Updated last year
- Persistent dense gemm for Hopper in `CuTeDSL`☆15Updated 2 months ago
- Debug print operator for cudagraph debugging☆14Updated last year
- FractalTensor is a programming framework that introduces a novel approach to organizing data in deep neural networks (DNNs) as a list of …☆29Updated 10 months ago