Hackernews posts about CUDA

1. 01
   

   newCUDA for AMD on Windowsgithub.com

   ▲ 175chiassedu8022d💬 109savesaved
2. 02
   

   newShow HN: Agentic CUDA Kernel Optimizergithub.com

   ▲ 37bertaye11d💬 11savesaved
3. 03
   

   newCUDA Rust: Two Tracks for Writing GPU Kernelsdeveloper.nvidia.com

   ▲ 12xiaoyu200626ddiscusssavesaved
4. 04
   

   newIntroducing CUDA Rust: Two Tracks for Writing GPU Kernelsdeveloper.nvidia.com

   ▲ 12ubj27ddiscusssavesaved
5. 05
   

   newKernelBench: Can LLMs Write GPU Kernels? – Benchmark and Toolkit, Torch –> CUDAgithub.com

   ▲ 6peter_d_sherman4ddiscusssavesaved
6. 06
   

   newShow HN: CUDA/graphics in QEMU-KVM VMs without passing the Nvidia card to themgithub.com

   ▲ 5reindertpelsma28d💬 2savesaved
7. 07
   

   newCUDA Rust: Two Tracks for Writing GPU Kernelsdeveloper.nvidia.com

   ▲ 5thomasfromcdnjs19ddiscusssavesaved
8. 08
   

   newCUDA Rust: Two Tracks for Writing GPU Kernelsdeveloper.nvidia.com

   ▲ 5Jhsto26ddiscusssavesaved
9. 09
   

   new"The CUDA Moat is Gone" – TechTechPotato with AI& founder David Bennet [video]www.youtube.com

   ▲ 4olvy024ddiscusssavesaved
10. 10
    

    newCUDA Rust: Two Tracks for Writing GPU Kernelsdeveloper.nvidia.com

    ▲ 4vertigoruntime28ddiscusssavesaved
11. 11
    

    newShow HN: CUDA-verkle – GPU-accelerated 256-MSM for Verkle tree commitmentsgithub.com

    ▲ 3grobat7912ddiscusssavesaved
12. 12
    

    newZLUDA – Drop-In Replacement for CUDA on Non-Nvidia GPUsgithub.com

    ▲ 2peter_d_sherman22d💬 1savesaved
13. 13
    

    newPTXBench: What about just CUDA-PTX?zhang677.github.io

    ▲ 2matt_d6ddiscusssavesaved
14. 14
    

    newCUDA Device Max Connectionsleimao.github.io

    ▲ 2eigenBasis9ddiscusssavesaved
15. 15
    

    newNvidia Expands Open Source CUDA-Q Platform for Fault-Tolerant Quantum Computingnvidianews.nvidia.com

    ▲ 2noobplus20ddiscusssavesaved
16. 16
    

    newInto the CUDA Multiverse of Runtime Compilation: GPU DBMS Kernel Fusion [pdf]www.vldb.org

    ▲ 2matt_d20ddiscusssavesaved
17. 17
    

    newCUDA Rust: Two Tracks for Writing GPU Kernelsdeveloper.nvidia.com

    ▲ 2CoderLim11022ddiscusssavesaved
18. 18
    

    newDeepJIT: Header-Only C++20 JIT Runtime for Nvidia CUDA and Huawei Ascendgithub.com

    ▲ 2mehmetoguzderin26ddiscusssavesaved
19. 19
    

    newShow HN: Reflex – a GGUF/CUDA inference engine tuned for cold-start latencygithub.com

    ▲ 1leochong12d💬 1savesaved
20. 20
    

    newMost CUDA tutorials introduce too much too earlycomputejunkie.substack.com

    ▲ 1ell-hol2hdiscusssavesaved
21. 21
    

    newCUDA Tile (cuTile) first working port in Javagithub.com

    ▲ 1birdculture22ddiscusssavesaved
22. 22
    

    newLaunch HN: Magnitude (YC S25) – Self-optimizing inference engine for agentsgithub.com

    ▲ 194anerli5d💬 99savesaved
23. 23
    

    newShow HN: TurboGPT: train 22KiB transformer in 13sgithub.com

    ▲ 56lostmsu6d💬 10savesaved
24. 24
    

    newShow HN: InstinctFlash – High-Performance Serving Runtime for Robotics Modelsgithub.com

    ▲ 27guanming071713d💬 4savesaved
25. 25
    

    newShow HN: Jinfer – AI inference engine for the JVM. AI in a jarqxotic.ai

    ▲ 6mukel21d💬 1savesaved
26. 26
    

    newShow HN: Optimized runtimes for three VLAs on Jetson Thorgithub.com

    ▲ 2hhuytho13ddiscusssavesaved
27. 27
    

    newFlashRec – Wide-beam generative recommendation. Every SID is a real item

    ▲ 1vect0ry7ddiscusssavesaved
28. 28
    

    newShow HN: PicoLM v1.0-rc2 ("Yura Kana"). Run an LLM on Digital Unixgithub.com

    ▲ 1gabucino12ddiscusssavesaved
29. 29
    

    newNvidia announces native GPU programming in Rustdeveloper.nvidia.com

    ▲ 970nonmaskable20d💬 404savesaved
30. 30
    

    newDeepSeek open sourced their Huawei Ascend programming stackaistockwire.com

    ▲ 5ashish013ddiscusssavesaved

· edit