HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
691.
▲
Acestep.cpp: portable C++17 implementation of ACE-Step 1.5 using GGML
github.com/ServeurpersoCom
discuss
3 months ago
qxip
3 points
692.
▲
Ggml C++ port of VITS for text-to-speech
github.com/maxilevi
discuss
3 months ago
maxilevi
3 points
693.
▲
To Use Snapdragon NPU, HTP Ops Libraries Must Be Signed with Trusted Certs
github.com/qualcomm
discuss
5 months ago
WhereIsTheTruth
3 points
694.
▲
Deepseek CPP for CPU only inference
github.com/andrewkchan
discuss
a year ago
amrrs
3 points
695.
▲
Whisper.cpp: Looking for Maintainers
github.com/ggerganov
discuss
a year ago
tech234a
3 points
696.
▲
A JDBC style C++ driver for Super High-performance CrossDB database
github.com/crossdb-org
discuss
2 years ago
jcwang
3 points
697.
▲
Distributed LLM Inference with Llama.cpp
github.com/ggerganov
discuss
2 years ago
tosh
3 points
698.
▲
Control Vectors have been added to llama.cpp
github.com/ggerganov
discuss
2 years ago
Der_Einzige
3 points
699.
▲
Gemma.cpp: lightweight, standalone C++ inference engine for Gemma models
github.com/google
discuss
2 years ago
ot
3 points
700.
▲
Llama.cpp supports distributed inference across machines on a local network
github.com/ggerganov
discuss
2 years ago
behnamoh
3 points
701.
▲
CUDA: Faster Mixtral Prompt Processing
github.com/ggerganov
discuss
3 years ago
tosh
3 points
702.
▲
Llama.cpp: Support for Phi-2
github.com/ggerganov
discuss
3 years ago
tosh
3 points
703.
▲
QMoE Support for Mixtral
github.com/ggerganov
discuss
3 years ago
tosh
3 points
704.
▲
Llama 2: poc for running 70B on CPU
github.com/ggerganov
discuss
3 years ago
tosh
3 points
705.
▲
Inference at the edge: Efficient transformer model inference on-device
github.com/ggerganov
discuss
3 years ago
lioeters
3 points
706.
▲
K-Quants
github.com/ggerganov
discuss
3 years ago
tosh
3 points
707.
▲
Llama.cpp: Add GPU support to ggml
github.com/ggerganov
discuss
3 years ago
mromanuk
3 points
708.
▲
Modern C++ OpenSSL Examples
github.com/RaymiiOrg
discuss
3 years ago
jandeboevrie
3 points
709.
▲
Bloomz.cpp: C++ implementation for BLOOM models
github.com/NouamaneTazi
discuss
3 years ago
Karuma
3 points
710.
▲
Show HN: A Simple library for progress bars in C++
github.com/Llawliet0872
discuss
5 years ago
hyper_frog
3 points
711.
▲
Ixy.cpp: A high-speed user space network driver written in C++
github.com/ackxolotl
discuss
6 years ago
ackxolotl
3 points
712.
▲
Awesome Modern C++
github.com/rigtorp
discuss
7 years ago
htfy96
3 points
713.
▲
A collection of resources on modern C++
github.com/rigtorp
discuss
8 years ago
sangar
3 points
714.
▲
LLM quantization severely damages model quality and perplexity
github.com/ggerganov
3 comments
3 years ago
behnamoh
2 points
715.
▲
Llama.cpp with CUDA Support on Original Jetson Nano (4GB)
github.com/kreier
2 comments
3 months ago
Abishek_Muthian
2 points
716.
▲
Modern C++ learning repo with code, projects, and interview questions
github.com/0voice
1 comment
7 months ago
ysy63874
2 points
717.
▲
CPFloat: A C Library for Simulating Low-Precision Arithmetic
github.com/north-numerical-computing
1 comment
2 years ago
blacksqr
2 points
718.
▲
Bloom Filter Implemention in C++
github.com/siara-cc
1 comment
3 years ago
siara-cc
2 points
719.
▲
Show HN: Turboquant.cpp – Quantize embeddings to 1-4 bits, no training (400 LoC)
github.com/RunEdgeAI
discuss
10 days ago
andrewmikhail
2 points
720.
▲
GW-Basic (Modern Cross-Platform Rewrite)
github.com/dagrigorev
discuss
a month ago
BruceEel
2 points
More