Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
781.
▲
Show HN: Realtime LLM Chat on an 8GB Nvidia GPU
(github.com/andybarry)
1 point
z991
3 years ago
discuss
782.
▲
NixOS for Nvidia Jetson Devices
(github.com/anduril)
1 point
gopherhunter
4 years ago
discuss
783.
▲
Id Tech 4 being ported to Nvidia's NVRHI
(github.com/RobertBeckebans)
1 point
jakearmitage
4 years ago
discuss
784.
▲
M.2 NVMe SSD Adapter for PC Engines APU2 Boards
(github.com/florolf)
1 point
walterbell
4 years ago
discuss
785.
▲
Thin C++-Flavored Wrappers for the CUDA APIs: Runtime, Driver, NVRTC and NVTX
(github.com/eyalroz)
1 point
einpoklum
4 years ago
discuss
786.
▲
Verified Instruction-Level Energy Consumption Measurement for Nvidia GPUs
(github.com/NMSU-PEARL)
1 point
pizza
4 years ago
discuss
787.
▲
Grate - open-source Nvidia Tegra driver
(github.com/grate-driver)
1 point
cunidev
5 years ago
discuss
788.
▲
Self-Hosted IPTV/NVR/CCTV/Video Service
1 point
fastocloud
6 years ago
discuss
789.
▲
Dockerized folding home client, with Nvidia GPU support
(github.com/codingCoffee)
1 point
coding_coffee
6 years ago
discuss
790.
▲
macOS EGPU Support for Nvidia and AMD
(github.com/learex)
1 point
tosh
6 years ago
discuss
791.
▲
Experimental project to get Java debugging via jdt.ls and coc.nvim
(github.com/dansomething)
1 point
adelarsq
6 years ago
discuss
792.
▲
Use fzf instead of coc.nvim built-in fuzzy finder
(github.com/antoinemadec)
1 point
Avi-D-coder
6 years ago
discuss
793.
▲
Show HN: A Photorealistic Path Tracer with NVIDIA RTX
(github.com/maierfelix)
1 point
Schampu
7 years ago
discuss
794.
▲
PyTorch Implementation of Nvidia Progressive Growing of GAN
(github.com/nashory)
1 point
stellastra
9 years ago
discuss
795.
▲
Guide on Running Nvidia EGPUs (with CUDA) on MacOS – Updated with High Sierra
(github.com/marnovo)
1 point
mnovaes
9 years ago
discuss
796.
▲
Change “nvim” to “ni” everywhere
(github.com/neovim)
1 point
gaving
10 years ago
discuss
797.
▲
Java Version Manager inspired by nvm
(github.com/shyiko)
1 point
shyiko
10 years ago
discuss
798.
▲
Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks
(github.com/antoinezambelli)
687 points
zambelli
a month ago
252 comments
799.
▲
We fine-tuned Llama 405B on AMD GPUs
(publish.obsidian.md)
495 points
felarof
2 years ago
101 comments
800.
▲
Show HN: Open-source x64 and Arm GitHub runners
(ubicloud.com)
475 points
umur
2 years ago
124 comments
801.
▲
Show HN: 80% faster, 50% less memory, 0% loss of accuracy Llama finetuning
(github.com/unslothai)
385 points
danielhanchen
3 years ago
119 comments
802.
▲
Launch HN: Silurian (YC S24) – Simulate the Earth
338 points
rejuvyesh
2 years ago
141 comments
803.
▲
Show HN: Banan-OS, an Unix-like operating system written from scratch
(github.com/Bananymous)
333 points
Bananymous
2 years ago
63 comments
804.
▲
Show HN: Moonshine Open-Weights STT models – higher accuracy than WhisperLargev3
(github.com/moonshine-ai)
316 points
petewarden
4 months ago
81 comments
805.
▲
Show HN: Tach – Visualize and untangle your Python codebase
(github.com/gauge-sh)
263 points
the1024
a year ago
62 comments
806.
▲
Show HN: GPT-2 implemented using graphics shaders
(github.com/nathan-barry)
228 points
nathan-barry
a year ago
25 comments
807.
▲
Show HN: Run TRELLIS.2 Image-to-3D generation natively on Apple Silicon
(github.com/shivampkumar)
202 points
shivampkumar
2 months ago
40 comments
808.
▲
Less Slow C++
(github.com/ashvardanian)
198 points
ashvardanian
a year ago
97 comments
809.
▲
Show HN: A physically-based GPU ray tracer written in Julia
(makie.org)
198 points
simondanisch
4 months ago
92 comments
810.
▲
Launch HN: Deepsilicon (YC S24) – Software and hardware for ternary transformers
189 points
areddyyt
2 years ago
79 comments
More