triton-inference-server / perf_analyzer

Related projects: ⓘ

• triple-Mu / TensorRT2ONNX
  A tool convert TensorRT engine/plan to a fake onnx
  ☆37Updated last year
• weishengying / cutlass_flash_atten_fp8
  使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention
  ☆46Updated last month
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆93Updated last week
• OpenPPL / ppl.kernel.cuda
  ☆32Updated 3 months ago
• latentCall145 / channels-last-groupnorm
  A CUDA kernel for NHWC GroupNorm for PyTorch
  ☆14Updated 2 weeks ago
• yester31 / Cutlass_EX
  study of cutlass
  ☆18Updated last year
• jundaf2 / CUDA-INT8-GEMM
  CUDA 8-bit Tensor Core Matrix Multiplication based on m16n16k16 WMMA API
  ☆22Updated last year
• leimao / Nsight-Compute-Docker-Image
  Nsight Compute in Docker
  ☆11Updated 8 months ago
• Bruce-Lee-LY / cuda_hgemv
  Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.
  ☆40Updated last week
• kilianhae / FlashAttention.C
  Flash Attention in raw Cuda C beating PyTorch
  ☆11Updated 4 months ago
• Oneflow-Inc / serving
  OneFlow Serving
  ☆20Updated 7 months ago
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆82Updated 6 months ago
• triton-inference-server / tensorrt_backend
  The Triton backend for TensorRT.
  ☆59Updated last week
• triton-inference-server / common
  Common source, scripts and utilities shared across all Triton repositories.
  ☆62Updated last week
• Archermmt / yolov3_dcn_nv_hackthon2021
  ☆10Updated 3 years ago
• AXERA-TECH / CLIP-ONNX-AX650-CPP
  ☆17Updated 3 months ago
• triple-Mu / HunyuanDiT-TensorRT-libtorch
  HunyuanDiT with TensorRT and libtorch
  ☆15Updated 3 months ago
• Oneflow-Inc / oneflow-xrt
  ☆22Updated last year
• Bruce-Lee-LY / flash_attention_inference
  Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.
  ☆20Updated last week
• li199603 / sgemm_with_cuda
  ☆13Updated 5 months ago
• MARD1NO / FxxkCUDA
  ☆52Updated this week
• daquexian / web-model-converter
  ☆33Updated last year
• hova88 / CUDA-MatMul-Practice
  ☆14Updated 8 months ago
• Oneflow-Inc / oneflow_convert
  OneFlow->ONNX
  ☆41Updated last year
• TRT2022 / trtllm-llama
  ☢️ TensorRT 2023复赛——基于TensorRT-LLM的Llama模型推断加速优化
  ☆40Updated 11 months ago
• DD-DuDa / Cute-Gemm-Optimization
  ☆15Updated last week
• FeiGeChuanShu / trt2023
  NVIDIA TensorRT Hackathon 2023复赛选题：通义千问Qwen-7B用TensorRT-LLM模型搭建及优化
  ☆39Updated 11 months ago
• zeroine / cutlass-cute-sample
  ☆18Updated 5 months ago
• ozanarmagan / clip_tokenizer_cpp
  ☆10Updated 2 months ago
• OpenPPL / ppl.pmx
  ☆56Updated this week