Hackernews posts about bfloat16

1. llm.c: multi-GPU, bfloat16, flash attention, ~7% faster than PyTorch (twitter.com)
   121 points by tosh over 1 year ago | 10 comments
2. Supporting BFLOAT16 in Fortran: "Not Recommended"? (fortran-lang.discourse.group)
   7 points by ggraphilia over 1 year ago | 2 comments
3. SQLite-Vector adds support for float16 and bfloat16 (CPU, NEON, AVX2 and SSE2) (github.com)
   4 points by marcobambini about 1 month ago | discuss
4. Evaluation of Bfloat16, Posit, and Takum Arithmetics in Sparse Linear Solvers (arxiv.org)
   3 points by jobstijl 9 months ago | 2 comments
5. BFloat16: The secret to high performance on Cloud TPUs (cloud.google.com)
   3 points by mfiguiere over 1 year ago | 1 comments
6. RISC-V with Linux 6.15 Adds Support for BFloat16 "BF16" Instructions (www.phoronix.com)
   2 points by jrepinc 6 months ago | discuss
7. llama.cpp bfloat16 support (github.com)
   2 points by indigodaddy over 1 year ago | discuss
8. Supporting BFLOAT16 in ISO_Fortran_env: not recommended (j3-fortran.org)
   1 points by zaikunzhang over 1 year ago | 7 comments
9. Converging Harmonic Series with bfloat16 (github.com)
   1 points by octocop almost 2 years ago | 1 comments
10. Scale 1.3 Adds BFloat16 and New Features for Compiling CUDA Apps on AMD GPUs (www.phoronix.com)
    1 points by latchkey 5 months ago | discuss
11. Show HN: Dive into Transformers and LLM World – Llama 3.1 in Go, Step by Step (github.com)
    4 points by adalkiran about 1 year ago | 2 comments
12. Show HN: SQLite AI - Open-Source Extensions to Bring AI to SQLite, Everywhere
    4 points by marcobambini 2 months ago | discuss
13. Show HN: LLaMA Nuts and Bolts, A holistic way of understanding how LLMs run (github.com)
    3 points by adalkiran over 1 year ago | discuss
14. Ask HN: Clarify VRAM usage during LLM forward pass
    1 points by furiousteabag almost 2 years ago | discuss
15. Show HN: Free AI Mobile App Generator (bfloat.ai)
    1 points by albystein 7 months ago | 2 comments