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. A complete Llama2 inference engine that fits in 1356 bytes of x86 assembly (github.com)
   27 points by monax 18 days ago | discuss
2. Meta abandons open-source Llama for proprietary Muse Spark (thenewstack.io)
   15 points by CrankyBear 22 days ago | 1 comments
3. Bleeding Llama: Critical Unauthenticated Memory Leak in Ollama (www.cyera.com)
   10 points by nateb2022 14 days ago | 1 comments
4. Meta abandons open-source Llama for proprietary Muse Spark (thenewstack.io)
   6 points by Nars088 19 days ago | 2 comments
5. WebGPU support in llama.cpp (reeselevine.github.io)
   5 points by relivin about 23 hours ago | discuss
6. Apple MLX vs. llama.cpp: compared and benchmarked [video] (www.youtube.com)
   5 points by nvahalik 15 days ago | discuss
7. Llama.cpp MIPS R8000 Kernel Running on an SGI Power Challenge from 1995 (twitter.com)
   4 points by MrBuddyCasino 23 days ago | discuss
8. Hardware LLM Taalas Reaches >14,000 TPS on Llama 3.1 8B (taalas.com)
   3 points by nullbio 1 day ago | 1 comments
9. Tracing tokens through Llama 3.1 8B inference on H100s (krithik.xyz)
   3 points by krithik_7 13 days ago | 1 comments
10. PFlash: 10x prefill speedup over llama.cpp at 128K on a RTX 3090 (github.com)
    3 points by GreenGames 21 days ago | 1 comments
11. WebGPU back end in llama.cpp/ggml (twitter.com)
    3 points by tosh about 4 hours ago | discuss
12. Llama.ttf: a font file which is also a large language model and inference engine (fuglede.github.io)
    3 points by smitec 19 days ago | discuss
13. World AI Agents–35 AI Models (Claude, GPT, Llama)via One OpenAIcompatible API (world-ai-agents.com)
    2 points by fazyyy 20 days ago | 1 comments
14. Show HN: Llama CPU Benchmarks (deemwar-products.github.io)
    2 points by muthuishere 2 days ago | discuss
15. Benchmarking llama.cpp's new MTP support on Strix Halo (calebcoffie.com)
    2 points by CCoffie 4 days ago | discuss
16. Llama.cpp b9180: MTP support landed (github.com)
    2 points by usagisushi 5 days ago | discuss
17. ZML: Between Jax and Llama.cpp (jaco-bro.github.io)
    2 points by jaco-bro 10 days ago | discuss
18. The AI scaffolding layer is collapsing. LlamaIndex's CEO explains what survives (venturebeat.com)
    2 points by momentmaker 21 days ago | discuss
19. Gemma 4 architecture support for QVAC-Fabric (Tether's llama.cpp fork) (github.com)
    2 points by oliveskin 23 days ago | discuss
20. Llama 4: A Deep Dive into Liquid Transformers 2.0 and Sovereign AI (en.landingfymax.com.br)
    2 points by EvCarvalho 28 days ago | discuss
21. ClickBook – Offline Android eReader with local LLM inference via llama.rn (play.google.com)
    1 points by elcooo 6 days ago | 1 comments
22. A 13-month-old LlamaIndex bug re-embeds unchanged content (sebastiantirelli.com)
    1 points by tirelli 28 days ago | 1 comments
23. Show HN: Llama-dash – local LLM operators dashboard and proxy (github.com)
    1 points by ndom91 3 days ago | discuss
24. Find bugs in YOUR code using OpenCode, Llama.cpp and Qwen3.6 (wtarreau.blogspot.com)
    1 points by falava 3 days ago | discuss
25. Llama and Spec: MTP Support (github.com)
    1 points by jhoho 15 days ago | discuss
26. Meta abandons open-source Llama for proprietary Muse Spark (thenewstack.io)
    1 points by Brajeshwar 21 days ago | discuss
27. Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks (github.com)
    673 points by zambelli 3 days ago | 247 comments
28. Show HN: Bonsai 1.7B ternary model at 442T/s on M4 Max (agents2agents.ai)
    13 points by hhuytho 18 days ago | 3 comments
29. Show HN: Smile-Serve – Inference Server for ML, ONNX, and LLM (github.com)
    5 points by haifeng 18 days ago | discuss
30. Show HN: Valkyr LM Inference with Realtime Guarantees (github.com)
    3 points by quatonion 19 days ago | discuss