HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
31.
▲
18 Years
github.com/paulusmack
1 comment
6 years ago
montzark
1 points
32.
▲
Show HN: Collaboratively Edit Draw.io Diagrams in VS Code
github.com/hediet
1 comment
6 years ago
Gehinnn
6 points
33.
▲
Hiring: full-time dev/systems hybrid at profitable, growing startup in Austin
jobs.github.com
discuss
14 years ago
jasford
2 points
34.
▲
Tell HN: Anima/Shun (YC W21) Considered Harmful
14 comments
2 years ago
JCharante
26 points
35.
▲
Postwire is hiring engineers to solve the content personalization problem
jobs.github.com
discuss
13 years ago
craigdaniel
3 points
36.
▲
On my first day, I was told:'Payment will come later, shouldn't be hard right?
github.com/getlago
discuss
4 years ago
thibo_skabgia
3 points
37.
▲
AI Study Assistant – Ask questions from your own notes
2 comments
a year ago
RajGuruYadav
2 points
38.
▲
Karpathy: Let's reproduce GPT-2 (1.6B): one 8XH100 node 24h $672 in llm.c
github.com/karpathy
58 comments
2 years ago
alecco
182 points
39.
▲
8x Nvidia GTX 1080 Hashcat Benchmarks
gist.github.com
83 comments
10 years ago
biggerfisch
133 points
40.
▲
Ollama 0.1.32: WizardLM 2, Mixtral 8x22B, macOS CPU/GPU model split
github.com/ollama
55 comments
2 years ago
tosh
107 points
41.
▲
Show HN: Code interpreter with mixtral-8x7B-instruct
github.com/stellar-amenities
discuss
3 years ago
sonlight03
35 points
42.
▲
Lodash - Drop-in replacement for Underscore.js with upto 8x perf improvements
github.com/bestiejs
3 comments
14 years ago
padolsey
16 points
43.
▲
Show HN: Like grep but for natural questions. Mixtral 8x7B – 28 tok/s on 8GB GPU
github.com/moritztng
discuss
2 years ago
molli
10 points
44.
▲
Show HN: NeuroFlow 55.8x video inference speedup for Vision Transformers PyTorch
github.com/ynnk-research
2 comments
a month ago
ynnk
8 points
45.
▲
Show HN: I embedded 685M public texts in 32 minutes (on 8x A100, Rust, TensorRT)
github.com/Artain-AI
discuss
18 days ago
ddayanov
7 points
46.
▲
TinyTTS: Ultra-light English TTS (9M params, 20MB), 8x CPU, 67x GPU
discuss
4 months ago
letrghieu
5 points
47.
▲
New Brim release: 4.8X speed boost to Windows version and more cool features
github.com/brimsec
discuss
6 years ago
siskojr
5 points
48.
▲
Show HN: Inference Mixtral 8x7B in pure Rust
github.com/moritztng
2 comments
2 years ago
molli
4 points
49.
▲
80x Faster Rust Code?
github.com/choiway
2 comments
6 years ago
choiway
4 points
50.
▲
Show HN: Speculative Decoding from Scratch in PyTorch (2.8x CPU Speedup)
github.com/kunal51107
1 comment
7 months ago
kunal51107
4 points
51.
▲
Run Mixtral-8x7B models in Colab or consumer desktops
github.com/dvmazur
discuss
2 years ago
tslmy
4 points
52.
▲
Cloning the Linux kernel in 30 seconds with gitoxide, 4.8x faster than Git
github.com/Byron
discuss
4 years ago
kibwen
4 points
53.
▲
Show HN: Zatron – Encrypted semantic search, 98% quality, 8x faster than FHE
github.com/zahraarmantech
discuss
21 days ago
zahraarman
3 points
54.
▲
Show HN: IgniteMS – batch text embeddings at 253K msg/s on 8x A100
github.com/Artain-AI
discuss
a month ago
ddayanov
3 points
55.
▲
Show HN: Distributed Storage System to 8x LLM Inference, GPU Training Efficiency
github.com/blackbird-io
discuss
8 months ago
hackerpanda123
3 points
56.
▲
Like grep but for natural language questions. Based on Mixtral 8x7B
github.com/moritztng
1 comment
2 years ago
homarp
2 points
57.
▲
4x-8x speedup in scikit-learn random forests
github.com/ajtulloch
discuss
12 years ago
ajtulloch
2 points
58.
▲
Show HN: Zmod codemod toolkit, 8x faster
github.com/NaamuKim
discuss
4 months ago
oss-luke
2 points
59.
▲
Show HN: WarpParse – Rust ETL engine 1.5–8x faster than Vector
discuss
5 months ago
warpparse
2 points
60.
▲
IndieSeas – Search engine for the indie web, based on 88x31 buttons
github.com/MrDaPoyo
discuss
a year ago
gnabgib
2 points
More