Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
91.
▲
Geziyor, a fast web crawling and scraping framework for Go
(github.com/geziyor)
4 points
jinqueeny
7 years ago
discuss
92.
▲
Llama.cpp now supports tool calling (OpenAI-compatible)
(github.com/ggerganov)
3 points
ochafik
a year ago
1 comment
93.
▲
GGML Flash Attention support merged into llama.cpp
(github.com/ggerganov)
3 points
smcleod
2 years ago
1 comment
94.
▲
Super Star Trek in the Browser
(github.com/ggeorgovassilis)
3 points
ggeorgovassilis
3 years ago
1 comment
95.
▲
Show HN: GPT-2 inference on the CPU using C/C++
(github.com/ggerganov)
3 points
ggerganov
4 years ago
1 comment
96.
▲
Show HN: Tweet2Doom – A Twitter bot that plays Doom
(github.com/ggerganov)
3 points
ggerganov
5 years ago
1 comment
97.
▲
Show HN: ggwave – tiny data-over-sound library
(github.com/ggerganov)
3 points
ggerganov
5 years ago
1 comment
98.
▲
Agent-town – A pixel-art AI agent online collaboration platform
(github.com/geezerrrr)
3 points
felixding
3 months ago
discuss
99.
▲
Whisper.cpp: Looking for Maintainers
(github.com/ggerganov)
3 points
tech234a
a year ago
discuss
100.
▲
TextMagic: A Next Generation of Text Input Based on Skia and Canvas
(github.com/gezilinll)
3 points
gezilinll
2 years ago
discuss
101.
▲
Distributed LLM Inference with Llama.cpp
(github.com/ggerganov)
3 points
tosh
2 years ago
discuss
102.
▲
Control Vectors have been added to llama.cpp
(github.com/ggerganov)
3 points
Der_Einzige
2 years ago
discuss
103.
▲
Llama.cpp supports distributed inference across machines on a local network
(github.com/ggerganov)
3 points
behnamoh
2 years ago
discuss
104.
▲
CUDA: Faster Mixtral Prompt Processing
(github.com/ggerganov)
3 points
tosh
2 years ago
discuss
105.
▲
Llama.cpp: Support for Phi-2
(github.com/ggerganov)
3 points
tosh
2 years ago
discuss
106.
▲
QMoE Support for Mixtral
(github.com/ggerganov)
3 points
tosh
2 years ago
discuss
107.
▲
Llama 2: poc for running 70B on CPU
(github.com/ggerganov)
3 points
tosh
3 years ago
discuss
108.
▲
Inference at the edge: Efficient transformer model inference on-device
(github.com/ggerganov)
3 points
lioeters
3 years ago
discuss
109.
▲
K-Quants
(github.com/ggerganov)
3 points
tosh
3 years ago
discuss
110.
▲
StableLM already being ported to ggml
(github.com/ggerganov)
3 points
theolivenbaum
3 years ago
discuss
111.
▲
Llama.cpp: Add GPU support to ggml
(github.com/ggerganov)
3 points
mromanuk
3 years ago
discuss
112.
▲
Tweet2Doom: A Twitter bot that plays Doom
(github.com/ggerganov)
3 points
ggerganov
5 years ago
discuss
113.
▲
Kbd-audio – Tools for capturing and analysing keyboard input paired with
(github.com/ggerganov)
3 points
pplonski86
8 years ago
discuss
114.
▲
LLM quantization severely damages model quality and perplexity
(github.com/ggerganov)
2 points
behnamoh
3 years ago
3 comments
115.
▲
Proteus: The AI-native editor for multimodal creation
(github.com/gezilinll)
2 points
gezilinll
5 months ago
1 comment
116.
▲
Self-hosted RSS reader with Docker and HTTPS
(github.com/ggeorgovassilis)
2 points
ggeorgovassilis
6 months ago
1 comment
117.
▲
I have implemented a GPU version of Pica which is high quailty image resizer
(github.com/gezilinll)
2 points
gezilinll
a year ago
1 comment
118.
▲
TextMagic: A Next Generation of Text Input Based on Skia and Canvas
(github.com/gezilinll)
2 points
gezilinll
2 years ago
1 comment
119.
▲
Collection of Linux Shell Scripts
(github.com/ggeorgovassilis)
2 points
ggeorgovassilis
2 years ago
1 comment
120.
▲
Show HN: r2t2 – Transmit data with the PC speaker
(github.com/ggerganov)
2 points
ggerganov
5 years ago
1 comment
More