Hackernews posts about CUDA C++

RSS feed for CUDA C++

01
newShow HN: CNET – Complex-valued neural networks from scratch in C++/CUDAgithub.com
▲ 2almaya 15d discuss
02
newDeepity – A C++/CUDA framework replacing backprop with predictive codinggithub.com
▲ 1jackrose2335 11d discuss
03
newWriting Speed-of-Light Flash Attention for 5090 in CUDA C++gau-nernst.github.io
▲ 159dsr12 440d 💬 34
04
newWhat about OpenCL and CUDA C++ alternatives?www.modular.com
▲ 25eatonphil 150d 💬 4
05
newFast Great-Circle Distance Calculation in CUDA C++developer.nvidia.com
▲ 4Alien1Being 139d discuss
06
newCUDA C++ Best Practices Guide [pdf]docs.nvidia.com
▲ 3throwawaybutwhy 454d 💬 1
07
newWhat Irregularity Costs: CUDA C++, Rust, and Tritonarxiv.org
▲ 3Jimmc414 87d discuss
08
newWhat about OpenCL and CUDA C++ alternatives?www.modular.com
▲ 2coffeeaddict1 375d 💬 1
09
newNvidia/Numba-CUDA-mlir: CUDA C++-style Python GPU compiler built on MLIRgithub.com
▲ 2nickwanninger 177d discuss
10
newShow HN: A Black Hole Simulator in CUDA C++github.com
▲ 2anwoy 261d discuss
11
newQuantized LLM training in pure CUDA/C++github.com
▲ 2ghuntley 402d discuss
12
newDemocratizing AI Compute, Part 5: What about CUDA C++ alternatives?www.modular.com
▲ 2shihab 611d discuss
13
newShow HN: I Am 15 and Built a Dual Backend MLP from Scratch Using CUDA C++github.com
▲ 1muchlakshay 472d 💬 2
14
newIro-CUDA-FFI – Rust orchestrates nvcc‑compiled CUDA C++ kernelsgithub.com
▲ 1tribe-iro 292d 💬 1
15
newDemocratizing AI Compute, Part 5: What about CUDA C++ alternatives?www.modular.com
▲ 1sparklychipmunk 610d discuss
16
newAsk HN: Resources for general purpose GPU development on Apple's M* chips?
▲ 149thinking_banana 681d 💬 82
17
newAsk HN: Are LeetCode interviews appropriate for senior/staff scientists?
▲ 3ipunchghosts 660d 💬 15
18
newShow HN: GPU-accelerated search for Bitcoin keys generated with weak entropyb4q.io
▲ 2orkblutt 262d 💬 1
19
newShow HN: Free GPUs in your terminal for learning CUDAgithub.com
▲ 2RohanAdwankar 351d discuss
20
newWhat to Learn? CUDA vs. PyTorch vs. Jax vs. Triton/Pallas
▲ 1bananc 355d 💬 1
21
newShow HN: Turkish Sieve Engine – Full Prime Statistics Up to 10^14 and V2 Previewgithub.com
▲ 1bilgisoft 239d discuss
22
newNvidia CUDA 13.3 Rolls Out CUDA Python 1.0, CUDA Tile for C++www.phoronix.com
▲ 1Bender 163d discuss
23
newShow HN: I built a tensor library from scratch in C++/CUDAgithub.com
▲ 119nirw4nna 506d 💬 28
24
newTurboOCR: 270–1200 img/s OCR with Paddle and TensorRT (C++/CUDA, FP16)github.com
▲ 7pfdomizer 207d 💬 4
25
newShow HN: A free, GPU-accelerated Texas Hold'em GTO solver in C++/CUDAbupticybee.github.io
▲ 5bupticybee 123d 💬 3
26
newThe creators of SQL, C++, CUDA, Haskell reviewed my book on Programming Historyhelloworldthebook.com
▲ 4DaleBiagio 178d discuss
27
newTernative – C++/CUDA inference engine for ternary LLMs with runtime LoRAgithub.com
▲ 3michelangeloro 171d 💬 1
28
newShow HN: TurboOCR up to 1200 pages/s with Paddle and TensorRT (C++/CUDA, FP16)github.com
▲ 3pfdomizer 204d discuss
29
newShow HN: Librediffusion: C++ / CUDA Reimplementation of StreamDiffusiongithub.com
▲ 3jcelerier 276d discuss
30
newShow HN: CNET – a C++/CUDA framework for researching complex valued NNgithub.com
▲ 2almaya 483d discuss
31
newShow HN: Agentic CUDA Kernel Optimizergithub.com
▲ 37bertaye 42d 💬 10
32
newShow HN: Multi-View Stereo Software for Rapid 3D Model Generation from 2D Imagesgithub.com
▲ 2aki_asahara 617d discuss