HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
271.
▲
Llama.cpp: Full CUDA GPU Acceleration
github.com/ggerganov
310 comments
3 years ago
gzer0
728 points
272.
▲
Running large language models like ChatGPT on a single GPU
github.com/Ying1123
264 comments
3 years ago
_nhynes
682 points
273.
▲
LibreCUDA – Launch CUDA code on Nvidia GPUs without the proprietary runtime
github.com/mikex86
145 comments
2 years ago
rrampage
643 points
274.
▲
We fine-tuned Llama 405B on AMD GPUs
publish.obsidian.md
101 comments
2 years ago
felarof
495 points
275.
▲
Nvidia Warp: A Python framework for high performance GPU simulation and graphics
github.com/NVIDIA
136 comments
2 years ago
jarmitage
490 points
276.
▲
$500 GPU outperforms Claude Sonnet on coding benchmarks
github.com/itigges22
284 comments
3 months ago
yogthos
489 points
277.
▲
Use your Nvidia GPU's VRAM as swap space on Linux
github.com/c0dejedi
126 comments
21 days ago
tanelpoder
472 points
278.
▲
Vgpu_unlock: Unlock vGPU functionality for consumer grade GPUs
github.com/DualCoder
132 comments
5 years ago
fragileone
468 points
279.
▲
BarraCUDA Open-source CUDA compiler targeting AMD GPUs
github.com/Zaneham
202 comments
4 months ago
rurban
464 points
280.
▲
Nvtop: Linux Task Monitor for Nvidia, AMD and Intel GPUs
github.com/Syllo
85 comments
2 years ago
alexzeitler
453 points
281.
▲
Show HN: Finetune LLaMA-7B on commodity GPUs using your own text
github.com/lxe
98 comments
3 years ago
lxe
449 points
282.
▲
DeepSeek Open Source FlashMLA – MLA Decoding Kernel for Hopper GPUs
github.com/deepseek-ai
108 comments
a year ago
helloericsf
441 points
283.
▲
High-Speed Large Language Model Serving on PCs with Consumer-Grade GPUs
github.com/SJTU-IPADS
83 comments
3 years ago
dataminer
417 points
284.
▲
Show HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPU
github.com/xaskasdf
101 comments
4 months ago
xaskasdf
395 points
285.
▲
CuPy: NumPy and SciPy for GPU
github.com/cupy
106 comments
2 years ago
tanelpoder
377 points
286.
▲
Exllamav2: Inference library for running LLMs locally on consumer-class GPUs
github.com/turboderp
125 comments
3 years ago
Palmik
322 points
287.
▲
PyTorch Library for Running LLM on Intel CPU and GPU
github.com/intel-analytics
95 comments
2 years ago
ebalit
308 points
288.
▲
SDL3 new GPU API merged
github.com/libsdl-org
122 comments
2 years ago
caspar
306 points
289.
▲
MLC-LLM: GPT/Llama on consumer-class GPUs and phones
github.com/mlc-ai
106 comments
3 years ago
junrushao1994
303 points
290.
▲
Right-sizes LLM models to your system's RAM, CPU, and GPU
github.com/AlexsJones
70 comments
4 months ago
bilsbie
301 points
291.
▲
RapidRAW: A non-destructive and GPU-accelerated RAW image editor
github.com/CyberTimon
126 comments
a year ago
l8rlump
278 points
292.
▲
A CPU that runs entirely on GPU
github.com/robertcprice
131 comments
4 months ago
cypres
272 points
293.
▲
Nx: Multi-dimensional tensors Elixir lib with multi-staged compilation (CPU/GPU)
github.com/elixir-nx
46 comments
5 years ago
thibaut_barrere
272 points
294.
▲
AMD GPU Inference
github.com/slashml
99 comments
2 years ago
fazkan
270 points
295.
▲
Rust-CUDA: Fast GPU code fully in Rust
github.com/RDambrosio016
85 comments
5 years ago
amadeusine
269 points
296.
▲
Zluda: CUDA on Intel GPUs
github.com/vosen
77 comments
5 years ago
fho
261 points
297.
▲
Reverse engineering Dell iDRAC to get rid of GPU throttling
github.com/l4rz
90 comments
3 years ago
f_devd
249 points
298.
▲
Vramfs – GPU VRAM based file system for Linux
github.com/Overv
77 comments
3 years ago
pabs3
243 points
299.
▲
炊紙(kashikishi) is a text editor that utilizes GPU to edit text in a 3D space
github.com/mitoma
101 comments
2 years ago
hiroshi3110
240 points
300.
▲
QEMU with VirtIO GPU Vulkan Support
gist.github.com
50 comments
2 years ago
GalaxySnail
239 points
More