Hackernews posts about Llama.cpp

1. We Found a Heap Overflow in Llama.cpp's Tokenizer (pwno.io)
   9 points by retr0reg 13 days ago | discuss
2. Hunyuan-A13B model support has been merged into llama.cpp (github.com)
   2 points by empire23 3 days ago | discuss
3. Show HN: A tool to benchmark LLM APIs (OpenAI, Claude, local/self-hosted) (llmapitest.com)
   55 points by mrqjr 12 days ago | 9 comments
4. Show HN: Local LLM Notepad – run a GPT-style model from a USB stick (github.com)
   40 points by davidye324 11 days ago | 9 comments
5. Show HN: Ebiose – A Darwin‑Style Playground for Self‑Evolving AI Agents (github.com)
   12 points by vincent-ebiose 9 days ago | 3 comments
6. Is GitHub Releases Down?
   5 points by rvz 24 days ago | 3 comments
7. Show HN: Local LLM Inference in Godot and Unity (github.com)
   2 points by nobodywho 4 days ago | 1 comments
8. Show HN: AGI-SaaS v1.0.0 – Modular Python RAG Framework for LLM Pipelines (github.com)
   1 points by diamajax 11 days ago | discuss
9. How Is LLaMa.cpp Possible? (finbarr.ca)
   685 points by birriel almost 2 years ago | 227 comments
10. Vision Now Available in Llama.cpp (github.com)
    550 points by redman25 2 months ago | 104 comments
11. Llama.cpp guide – Running LLMs locally on any hardware, from scratch (steelph0enix.github.io)
    368 points by zarekr 7 months ago | 87 comments
12. Heap-overflowing Llama.cpp to RCE (retr0.blog)
    248 points by retr0reg 4 months ago | 54 comments
13. Llama.cpp supports Vulkan. why doesn't Ollama? (github.com)
    217 points by buyucu 5 months ago | 228 comments
14. Ollama violating llama.cpp license for over a year (github.com)
    202 points by Jabrov about 2 months ago | 68 comments
15. Llama.cpp Now Supports Qwen2-VL (Vision Language Model) (github.com)
    155 points by BUFU 7 months ago | 50 comments
16. Show HN: LLaVaVision: An AI "Be My Eyes"-like web app with a llama.cpp backend (github.com)
    154 points by lxe over 1 year ago | 19 comments
17. Show HN: Open-source load balancer for llama.cpp (github.com)
    151 points by mcharytoniuk about 1 year ago | 20 comments
18. Go library for in-process vector search and embeddings with llama.cpp (github.com)
    114 points by kelindar 9 months ago | 29 comments
19. Llama.cpp AI Performance with the GeForce RTX 5090 Review (www.phoronix.com)
    113 points by kristianp 4 months ago | 78 comments
20. Performance of llama.cpp on Apple Silicon A-series (github.com)
    100 points by mobilio over 1 year ago | 41 comments
21. Running Llama.cpp on AWS Instances (github.com)
    96 points by schappim over 1 year ago | 10 comments
22. Llamanet: Zero-setup, zero-dependency OpenAI replacement powered by llama.cpp (github.com)
    45 points by cocktailpeanut about 1 year ago | 5 comments
23. 21.2× faster than llama.cpp? plus 40% memory usage reduction (arxiv.org)
    43 points by helloericsf about 1 year ago | 14 comments
24. Show HN: Grammar Generator App for Llama.cpp (grammar.intrinsiclabs.ai)
    19 points by aduffy almost 2 years ago | 6 comments
25. Gemma Is Added to Llama.cpp (github.com)
    17 points by behnamoh over 1 year ago | discuss
26. LLaVA C++ server (based on llama.cpp) (github.com)
    14 points by trzy over 1 year ago | 6 comments
27. Llama.cpp Now Part of the Nvidia RTX AI Toolkit (developer.nvidia.com)
    13 points by alanzhuly 9 months ago | 1 comments
28. Llama.cpp releases now ship with pre-built macOS binaries (twitter.com)
    12 points by schappim over 1 year ago | 1 comments
29. Grok-1 Support for Llama.cpp (github.com)
    11 points by schappim over 1 year ago | 2 comments
30. Jlama (Java) outperforms llama.cpp in F32 Llama 7B Model (twitter.com)
    7 points by tjake almost 2 years ago | 9 comments
31. Llama.cpp Working on Support for Llama3 (github.com)
    7 points by theolivenbaum about 1 year ago | discuss
32. DeepSeek-R1 speeds up llama.cpp code by x2 (github.com)
    6 points by roboboffin 5 months ago | 3 comments
33. Llama.cpp AI Performance with the GeForce RTX 5090 (www.phoronix.com)
    6 points by mfiguiere 5 months ago | 1 comments
34. llama.cpp now supports StarCoder model series (github.com)
    6 points by wsxiaoys almost 2 years ago | 1 comments
35. Show HN: LMQL becomes simpler and adds llama.cpp (lmql.ai)
    6 points by lbeurerkellner almost 2 years ago | discuss
36. Ask HN: 2x Arc A770 or 1x Radeon 7900 XTX for llama.cpp
    5 points by danielEM 4 months ago | 5 comments
37. Llama.http: A Dockerized, simple HTTP API for llama.cpp (hub.docker.com)
    5 points by edfletcher_t137 almost 2 years ago | 1 comments
38. Llama.cpp: SOTA 2-bit quants (github.com)
    5 points by tosh over 1 year ago | discuss