HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
241.
▲
Show HN: Llr – a Clojure inspired Lisp that compiles to R in R
github.com/dirkschumacher
17 comments
5 years ago
watwatwat123
63 points
242.
▲
Full forward pass of GPT-2 in one file of pure CUDA
github.com/karpathy
4 comments
2 years ago
tosh
63 points
243.
▲
Show HN: Phorth – A Forth-like language on the Python VM
github.com/llllllllll
14 comments
9 years ago
joejev
62 points
244.
▲
GitHub – Karpathy/LLM101n: LLM101n: Let's Build a Storyteller
github.com/karpathy
7 comments
2 years ago
bilsbie
61 points
245.
▲
Llama2.rs: One-file Rust implementation of Llama2
github.com/srush
10 comments
3 years ago
sshroot
60 points
246.
▲
llgo: compiler for Go, written in Go, using LLVM compiler infrastructure
github.com/axw
3 comments
14 years ago
jemeshsu
60 points
247.
▲
Virtual memory overhead for trees
github.com/johnj
19 comments
14 years ago
zippie
59 points
248.
▲
LLVM backend for m88k architecture
github.com/redstar
10 comments
4 years ago
fcambus
59 points
249.
▲
Circuit-level PDP-11/34 emulator
github.com/dbrll
8 comments
3 months ago
elvis70
59 points
250.
▲
Llama2-shepherd a CLI tool to install multiple implementations of the llama2
github.com/mikepapadim
8 comments
2 years ago
mikepapadim
59 points
251.
▲
Propeller: Profile-guided, optimizing, large-scale LLVM-based relinker
github.com/google
27 comments
6 years ago
uluyol
56 points
252.
▲
Optimizing Clang: A Practical Example of Applying Bolt
github.com/llvm
discuss
4 years ago
cpeterso
55 points
253.
▲
Show HN: Using LLama2 to Correct OCR Errors
github.com/Dicklesworthstone
10 comments
3 years ago
eigenvalue
54 points
254.
▲
Practical Llama 3 inference implemented in a single Java file
github.com/mukel
3 comments
2 years ago
dgiagio
54 points
255.
▲
Show HN: Get lists of files in a directory that contains a large number of files
github.com/catatsuy
29 comments
5 years ago
catatsuy
53 points
256.
▲
Show HN: LLMWare – Small Specialized Function Calling 1B LLMs for Multi-Step RAG
github.com/llmware-ai
6 comments
2 years ago
doberst0103
51 points
257.
▲
Comments on optimizations around string concatenation
gist.github.com
14 comments
6 years ago
jbredeche
49 points
258.
▲
Show HN: Llama Running on a Microcontroller
github.com/maxbbraun
5 comments
3 years ago
maxbbraun
49 points
259.
▲
Revec: Program Rejuvenation Through Revectorization
github.com/revec
5 comments
7 years ago
homarp
49 points
260.
▲
Llvm-Cbe: Resurrected LLVM “Bitcode to C Back End” with Improvements
github.com/JuliaComputing
11 comments
10 years ago
vmorgulis
48 points
261.
▲
Show HN: Llama – Terminal File Manager
github.com/antonmedv
6 comments
4 years ago
medv
48 points
262.
▲
Show HN: Chat with GPT about medical issues, get answers from medical literature
github.com/clint-llm
19 comments
3 years ago
garrinm
45 points
263.
▲
Mark Zuckerberg himself appears in the list of direct contributors to Llama 3
github.com/meta-llama
17 comments
2 years ago
jonbraun
45 points
264.
▲
Llamanet: Zero-setup, zero-dependency OpenAI replacement powered by llama.cpp
github.com/pinokiocomputer
5 comments
2 years ago
cocktailpeanut
45 points
265.
▲
Clang: -Wexperimental-lifetime-safety: Experimental C++ Lifetime Safety Analysis
github.com/llvm
1 comment
a year ago
matt_d
42 points
266.
▲
Llilum: LLVM-based code generator for MSIL and UWP apps targeting microcontrollers
github.com/NETMF
2 comments
11 years ago
andyjohnson0
39 points
267.
▲
Show HN: Pytheus – Python Prometheus client built with multiprocessing in mind
github.com/Llandy3d
11 comments
3 years ago
llandy3d
35 points
268.
▲
Llama2.java: Karpathy's llama2.c ported to Java
github.com/mukel
18 comments
3 years ago
mukel
33 points
269.
▲
Show HN: Open Message Format – a compact, vendor-agnostic spec for messages
github.com/open-llm-initiative
16 comments
2 years ago
aayushwhiz
32 points
270.
▲
Show HN: LLM-Term – Simple Rust-based CLI assist tool
github.com/dh1011
11 comments
2 years ago
dh1011
32 points
More