Hackernews posts about Llama2

Llama2 is a large language model that has achieved impressive performance in natural language processing tasks, outperforming ChatGPT and other models in various benchmarks.

1. I patched llama.cpp to gain 20% prompt processing TPS. Help me make a PR
   6 points by i_am_rocoe 9 days ago | 2 comments
2. As; HN: I was curious why MTP affects PP TPS in llama.cpp. My PoC recovers it?
   4 points by i_am_rocoe 12 days ago | 1 comments
3. TurboPrefill: 2.7× faster than llama.cpp Pipeline Parallel on Llama-3-70B (github.com)
   3 points by trykhlieb 7 days ago | discuss
4. Llama.cpp flags auto-tuning tool (github.com)
   3 points by raketenkater 11 days ago | discuss
5. Show HN: Loqi, a "local-first" translation tool using Ollama/llama.cpp (github.com)
   3 points by danterolle 14 days ago | discuss
6. Second Brain – A free, invisible AI interview copilot (Groq and Llama 3) (github.com)
   3 points by hi2brain 16 days ago | discuss
7. Show HN: Best setup local LLM found for a 5090 (llama.cpp fork + turboquant) (local-llm.utop.workers.dev)
   2 points by utopman 30 days ago | 2 comments
8. Llama-dash – One go-to control plane for local inference (llama-dash.dev)
   2 points by ndom91 15 days ago | 1 comments
9. Show HN: Llama Legends - A 100% free Card Game with RPG elements (llamalegends.com)
   2 points by TheLuigiplayer 8 days ago | discuss
10. Show HN: MinLlama – Llama 3.2 inference in ~100 lines of NumPy (github.com)
    2 points by timothygao 14 days ago | discuss
11. Monitoring LLM Inference with Prometheus and Grafana (vLLM, TGI, Llama.cpp) (www.glukhov.org)
    2 points by nryoo 22 days ago | discuss
12. Llama.cpp – Run LLM Inference in C/C++ (llama-cpp.com)
    2 points by doener 23 days ago | discuss
13. LlamaIndex integration for SynapCores (RAG, GraphRAG, and hybrid retrieval) (github.com)
    1 points by Synapcores 10 days ago | 1 comments
14. Show HN: How clanker are you? A reverse Turing test (howclankerareyou.com)
    11 points by niklio 3 days ago | 10 comments
15. Show HN: Run AI chat, image gen, vision, and voice offline on your Mac (github.com)
    10 points by olie_h 7 days ago | 3 comments
16. The AI Conundrum: We are living in highly subsidized, interesting times
    10 points by pyeri 15 days ago | 1 comments
17. Ask HN: Any Local LLM can I run without GPU for Local Agentic workflow AI?
    8 points by limondas 26 days ago | 4 comments
18. Show HN: Selora – local model for Home Assistant (github.com)
    7 points by bayshark 19 days ago | 4 comments
19. Ask HN: How is GPU power draw measured at scale?
    6 points by anax32 11 days ago | 2 comments
20. Show HN: Peek – A Figma like DB GUI (getpeek.dev)
    6 points by tehrash 22 days ago | 1 comments
21. Show HN: Sipp – Run small local LLMs in browser 3x faster (www.sipp.sh)
    5 points by jjhartmann 12 days ago | 3 comments
22. What are you looking for when reviewing LLM generated code?
    4 points by gnunicorn 22 days ago | 1 comments
23. Show HN: role-model, a router for hybrid local/cloud AI (github.com)
    3 points by try-working 9 days ago | 2 comments
24. Ask HN: What are some good/fast coding models for Apple Silicon?
    2 points by LoganDark 20 days ago | 3 comments
25. Show HN: AI Agents the Unix Way – built with bash, curl, and jq (github.com)
    2 points by cloudkj 13 days ago | discuss
26. Show HN: PyTorch on Java (github.com)
    2 points by pdsminer 25 days ago | discuss
27. Show HN: Voice-to-SQL – ask a database in plain English (LLM → SQL) (huggingface.co)
    1 points by Squalillo 6 days ago | discuss
28. Show HN: Language1 – Benchmarking LLM comprehension of vague prompts via Taboo (language1.app)
    1 points by kaandemirel 18 days ago | discuss
29. Show HN: EzziwebTools – A collection of 30 free tools (ezziwebtools.com)
    1 points by Ezzymd 26 days ago | discuss
30. Markdown Comes to Liteparse (www.llamaindex.ai)
    5 points by pierre 18 days ago | 1 comments