Heykuki News

TopNewBestAskShowJobs
TopNewBestAskShowJobs
871.
A GPU-rendered terminal emulator with inline 3D graphics (github.com/orhun)
1 point
LelouBil
a month ago
discuss
872.
GPU-accelerated terminal environment in Zig (github.com/semos-labs)
1 point
begoon
a month ago
discuss
873.
Show HN: Qumulator – simulate 1k-qubit circuits on CPU, exact results, no GPU (github.com/qumulator)
1 point
nnoorbakhsh
a month ago
discuss
874.
ModelCascade – Route LLM calls to your own GPU first, cloud second (github.com/wayneColt)
1 point
wayneIA
2 months ago
discuss
875.
Limux: GPU-accelerated terminal multiplexer for Linux (github.com/am-will)
1 point
mariuz
2 months ago
discuss
876.
AluminatiAI – per-job GPU cost tracking (Nvidia-smi shows watts, not dollars)
1 point
AluminatiAi
3 months ago
discuss
877.
Show HN: Go LLM inference with a Vulkan GPU back end that beats Ollama's CUDA (github.com/computerex)
1 point
computerex
3 months ago
discuss
878.
Show HN: ChronosBench – Terminal CPU/Metal GPU stress tester with live load bars (github.com/nishaantkumardas)
1 point
nish068
3 months ago
discuss
879.
Show HN: GPU multi-agent war simulation (github.com/ayushdnb)
1 point
luthor190397
3 months ago
discuss
880.
Show HN: WaveGuard – Anomaly detection using wave physics simulation (GPU, MCP) (github.com/gpartin)
1 point
waveguard
3 months ago
discuss
881.
Show HN: Train a 230KB text classifier from 50 examples – no API keys, no GPU (github.com/expressibleai)
1 point
veniyer
3 months ago
discuss
882.
A DataFrame Library Which Runs on GPUs, Accelerators and More (github.com/ronfriedhaber)
1 point
ronfriedhaber
4 months ago
discuss
883.
Show HN: Gflow – Lightweight single-node GPU job scheduler in Rust (github.com/AndPuQing)
1 point
PuQing
4 months ago
discuss
884.
Beautiful iOS SSH Terminal with GPU Acceleration (github.com/eriklangille)
1 point
dnw
4 months ago
discuss
885.
Show HN: NanoSLG – Hack Your Own Multi-GPU LLM Server (5x Faster, Educational) (github.com/Guney-olu)
1 point
geniusyan
4 months ago
discuss
886.
Local Agent Bench: Test 11 small LLMs on tool-calling judgment, on CPU, no GPU (github.com/MikeVeerman)
1 point
MikeVeerman
4 months ago
discuss
887.
Macmon: Sudoless performance monitoring for Apple processors. CPU / GPU / RAM us (github.com/vladkens)
1 point
fanf2
4 months ago
discuss
888.
PowerInfer: Fast LLM Inference on a Consumer-Grade GPU (github.com/Tiiny-AI)
1 point
oldfuture
4 months ago
discuss
889.
Pre-balanced GPU workload distribution inspired by octopus neural coordination (github.com/matthewlam721)
1 point
danny00
4 months ago
discuss
890.
Show HN: The Poor Man's Guide to Cloud GPU Selection (gist.github.com)
1 point
kyo_takano
4 months ago
discuss
891.
Show HN: Run Dia2 TTS Without a GPU (github.com/khariha)
1 point
quicheshore2003
5 months ago
discuss
892.
Show HN: Libcusort – A radix sort for modern Nvidia GPUs (github.com/IlyaGrebnov)
1 point
grebnov
5 months ago
discuss
893.
Show HN: NVMI – Open-Source – lightweight real-time Nvidia GPU monitor in Python (github.com/msrmdhcc)
1 point
msrmdhcc
5 months ago
discuss
894.
Nvidia said GPUDirect RDMA wasn't supported on Spark. We got RDMA working anyway (github.com/autoscriptlabs)
1 point
autoscriptlabs
5 months ago
discuss
895.
Autumnjs: Reactive, deterministic, GPU-aware, ultra-low-latency front end engine (github.com/renderhq)
1 point
handfuloflight
7 months ago
discuss
896.
Show HN: Qantify – GPU-Accelerated Trading Library with Advanced Math and AutoML (github.com/Alradyin)
1 point
Alradyin
7 months ago
discuss
897.
gdrcopy: Fast CPU-GPU memory copy library based on Nvidia GPUDirect RDMA (github.com/NVIDIA)
1 point
transpute
7 months ago
discuss
898.
Show HN: GPU Profiling That's Useful in 60 Seconds (keysandcaches.com)
1 point
technoabsurdist
10 months ago
discuss
899.
Show HN: PECU 3.0 – GPU passthrough and one-command VM templates for Proxmox 9 (github.com/Danilop95)
1 point
Danilop95
10 months ago
discuss
900.
Show HN: Energy-Efficient NAS via RBF Kernel Scoring (No GPU Training Needed) (youtube.com)
1 point
Tomomasa
a year ago
discuss
More