cuda 54 gpu 36 tensor 29 python 26 pytorch 23 scipy 23 nvtx 23 nvrtc 23 numpy 23 nccl 23 cutensor 23 cusparselt 23 cusparse 23 cusolver 23 curand 23 cupy 23 cudnn 23 cublas 23 amd 22 inferentia 22 tpu 22 xpu 21 transformer 21 trainium 21 model-serving 21 mlops 21 llmops 21 llm-serving 21 llm 21 llama 21 inference 21 gpt 21 deep-learning 8 performance 7 opencl 7 machine-learning 7 hpu 6 qwen 6 vulkan 6 tvm 6 spirv 6 metal 6 javascript 6 compiler 6 deepseek 6 parallel 5 openmp 5 quantum-machine-learning 4 quantum-computing 4 mpi 4 hpc 4 distributed-computing 4 cpp 3 ipi 2 jax 2 lammps 2 materials-science 2 molecular-dynamics 2 computational-chemistry 2 c 2 ase 2 nodejs 2 paddle 2 deepmd 2 potential-energy 2 tensorflow 2 learning 2 machine 2 hip 2 cprogramming 1 metadata 1 platform-independent 1 python-library 1 toml 1 performance portability 1 hiprtc 1 bindings 1 wrapper 1 Python 1 scientific 1 computing 1 GPU 1 HIP 1 serial 1 sycl 1 openmptarget 1 hpx 1 kokkos 1 parallelism 1 nvidia-smi 1 amdgpu 1 linux 1 underclocking 1 overclocking 1 monitoring 1 system 1 server 1 LLM 1 molecular dynamics 1 SPONGE 1