Heykuki News

TopNewBestAskShowJobs
TopNewBestAskShowJobs
781.
Less Slow C++ (github.com/ashvardanian)
198 points
ashvardanian
a year ago
97 comments
782.
Mistral Integration Improved in Llama.cpp (github.com/ggml-org)
95 points
decide1000
10 months ago
15 comments
783.
Llama.cpp: Add GPT-OSS (github.com/ggml-org)
35 points
atgctg
10 months ago
discuss
784.
Learning to Write Less Slow C, C++, and Assembly Code (github.com/ashvardanian)
15 points
asicsp
a year ago
discuss
785.
Building Blocks for Agents in C++ (github.com/mozilla-ai)
7 points
daavoo
6 months ago
discuss
786.
Yet another reminder why you should not use Ollama (github.com/ggml-org)
6 points
dcreater
4 months ago
5 comments
787.
Llama.cpp: Deterministic Inference Mode (CUDA): RMSNorm, MatMul, Attention (github.com/ggml-org)
6 points
diwank
9 months ago
discuss
788.
Show HN: Less Slow C++ (github.com/ashvardanian)
6 points
ashvardanian
a year ago
discuss
789.
Show HN: PVAC FHE over hypergraphs with LPN security (github.com/octra-labs)
5 points
0x0ffh_local
6 months ago
discuss
790.
IntelliJ Bug might make me end up switching editors (github.com/d-pollard)
4 points
marcusdigitz
3 years ago
5 comments
791.
GitHub deletes popular llama.cpp fork without explanation (github.com/ikawrakow)
4 points
akawry
a year ago
2 comments
792.
Rigid C++: A Pragmatic Architecture for High-Performance Systems (github.com/I-A-S)
4 points
I-A-S
9 days ago
1 comment
793.
Llama.cpp's Agents.md (github.com/ggml-org)
4 points
Wowfunhappy
2 months ago
1 comment
794.
Llama.cpp launches official WebUI for local LLMs (github.com/ggml-org)
4 points
victormustar
7 months ago
discuss
795.
Rust's vs. C++'s performance of a network driver implemented in both languages (github.com/ixy-languages)
4 points
ackxolotl
6 years ago
discuss
796.
Ixy.cpp: A high-speed user space network driver written in C++ (github.com/ixy-languages)
4 points
ackxolotl
6 years ago
discuss
797.
C++ Coroutines Resources (gist.github.com)
4 points
matt_d
7 years ago
discuss
798.
Claude Agent SDK C++ (github.com/0xeb)
3 points
0xeb
7 months ago
1 comment
799.
Year old IntelliJ bug is actively making my development experience miserable (github.com/d-pollard)
3 points
marcusdigitz
3 years ago
1 comment
800.
ik_llama.cpp – llama.cpp fork with better CPU performance (github.com/ikawrakow)
3 points
peter_d_sherman
7 days ago
discuss
801.
Grinder12: 0.96-Bit Lossless Streaming KV-Cache (16.55x VRAM Savings (github.com/ggml-org)
3 points
AMICLLC
a month ago
discuss
802.
Show HN: Kitten TTS Based Low-Latency Streaming Voice Assistant on CPU (github.com/abhishekgandhi-neo)
3 points
gauravvij137
3 months ago
discuss
803.
AMD teams contributing to the llama.cpp codebase (github.com/ggml-org)
3 points
gzer0
10 months ago
discuss
804.
Release Less Slow CPP v0.6: Thrust → CUDA → PTX → SASS (github.com/ashvardanian)
3 points
thunderbong
a year ago
discuss
805.
Stable Diffusion in pure C/C++ (github.com/leejet)
3 points
tim_sw
3 years ago
discuss
806.
Go Bindings for LLaMa.cpp (github.com/matthewrennie)
3 points
matthewrennie
3 years ago
discuss
807.
Dat Copy – remote file copy, powered by the Dat protocol (github.com/tom-james-watson)
3 points
lyri787w
8 years ago
discuss
808.
JavaScript/C++ Rosetta Stone – Reproducing the Behavior of JavaScript in C++ (github.com/Jeff-Mott-OR)
3 points
foob
9 years ago
discuss
809.
Intel CPU security features (github.com/huku-)
3 points
gbrown_
9 years ago
discuss
810.
CPU matrix-multiplication optimization suite (github.com/arun-reddy-a)
2 points
arun99-99
4 months ago
1 comment
More