HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
481.
▲
Pipeline-parallel LLM inference across GPUs on separate machines
github.com/leyten
discuss
5 days ago
ngaut
5 points
482.
▲
NodeMind – binary document index, 48× smaller than float32 RAG, no GPU required
github.com/QLNI
discuss
2 months ago
Nodemind
5 points
483.
▲
Zinc – LLM inference engine written in Zig, running 35B models on $550 AMD GPUs
github.com/zolotukhin
discuss
3 months ago
mvdwoord
5 points
484.
▲
Show HN: ClawMem – Open-source agent memory with SOTA local GPU retrieval
github.com/yoloshii
discuss
3 months ago
yoloshii
5 points
485.
▲
TinyTTS: Ultra-light English TTS (9M params, 20MB), 8x CPU, 67x GPU
discuss
4 months ago
letrghieu
5 points
486.
▲
Show HN: Axiom – C++ tensor library with NumPy API and Metal GPU support
discuss
5 months ago
noahkay13
5 points
487.
▲
Nvidia GPU: Discussing Blackwell's Limitations and Predicting Rubin
github.com/zartbot
discuss
5 months ago
yankcrime
5 points
488.
▲
Show HN: LLMKube – Kubernetes for Local LLMs with GPU Acceleration
github.com/defilantech
discuss
7 months ago
defilan
5 points
489.
▲
Show HN: Unrestricted Windows automation MCP with 9.68x GPU amplification
github.com/For-Sunny
discuss
7 months ago
Opus_Warrior
5 points
490.
▲
Show HN: 50+ LLMs on 2 GPUs with 2-Second Swapping? We built AI-Native Runtime
github.com/inferx-net
discuss
a year ago
pveldandi
5 points
491.
▲
NnScaler converts models designed for one GPU to run concurrently on multiple
github.com/microsoft
discuss
2 years ago
yeldarb
5 points
492.
▲
Pygfx/wgpu-py: Next generation GPU API for Python
github.com/pygfx
discuss
2 years ago
figomore
5 points
493.
▲
Pyhpc: Benchmarks for CPU and GPU of the most popular high-perf Python libs
github.com/dionhaefner
discuss
5 years ago
homarp
5 points
494.
▲
PyTorch GPU Acceleration for Apple’s M1 Chip
github.com/pytorch
discuss
5 years ago
yeldarb
5 points
495.
▲
DearPyGui 1.0.0: A GPU Accelerated Python GUI Framework
github.com/hoffstadt
discuss
5 years ago
illuminated
5 points
496.
▲
Nvidia-patch: disable NVENC and NvFCB restrictions on consumer-grade GPUs
github.com/keylase
discuss
5 years ago
NilsIRL
5 points
497.
▲
Deep Diamond (Deep Learning Library for GPU and CPU Written in Clojure)
github.com/uncomplicate
discuss
6 years ago
yamahadan
5 points
498.
▲
Show HN: Deepcluster.io, A cheap and easy to use GPU cluster for deep learning
discuss
7 years ago
yilu331
5 points
499.
▲
Alacritty: A cross-platform, GPU enhanced terminal emulator
github.com/jwilm
discuss
9 years ago
fuwuxopape
5 points
500.
▲
Show HN: I developed a node editor framework using gpui
github.com/tu6ge
4 comments
3 months ago
tu6ge
4 points
501.
▲
Local LLM Setup on Windows with Ollama and LM Studio (ThinkPad / RTX A3000 GPU)
github.com/gbro3n
3 comments
4 months ago
appsoftware
4 points
502.
▲
Aule-Attention, FlashAttention That Works on AMD GPUs
github.com/AuleTechnologies
3 comments
6 months ago
xenn0010
4 points
503.
▲
GPU Accelerated JavaScript Advanced Substation Alpha Subtitles Renderer (WIP)
github.com/SABRE-JS
3 comments
5 years ago
ILOVEPIE
4 points
504.
▲
Automated LTC mining on EC2 GPU instances using Ansible
github.com/adammeghji
2 comments
13 years ago
AdamMeghji
4 points
505.
▲
Online random forest in C++, uses the GPU with OpenCL.
github.com/albertvucinovic
2 comments
13 years ago
ilijavanil
4 points
506.
▲
Show HN: Bandmeter: Per-program network usage monitor for Linux, built with GPUI
github.com/emamoah
2 comments
3 months ago
emamoah
4 points
507.
▲
Show HN: ManasPDF – GPU-accelerated PDF renderer built from scratch in C++
github.com/Informal061
2 comments
4 months ago
informal061
4 points
508.
▲
TensorDict: A GPU-accelerated Python dictionary
github.com/pytorch
2 comments
2 years ago
vmoens
4 points
509.
▲
Nervana Systems releases Neon v0.9 today with multi-GPU support for Maxwells
github.com/NervanaSystems
1 comment
11 years ago
jessiclr
4 points
510.
▲
FMAG: A single-instruction GPU virtual machine and toolchain
github.com/jangafx
1 comment
7 days ago
adamrezich
4 points
More