genpfault

> https://github.com/darshi1337/apogee/blob/main/MODELS.md#loc...

> Unlike Ollama, [llama.cpp] serves one model at a time: the GGUF you launched it with.

FWIW: llama-server's supported multiple models for a while now:

https://github.com/ggml-org/llama.cpp/tree/master/tools/serv...

> At least the Catholics were consistent: it only took one new pope and one conclave before the Church declared that artificial intelligence also had the same right to life as fetuses and murderers.

https://www.miraclejones.com/stories/vitalics.html

> Just this week i've paid ~$1k USD for 2x32G DDR5 ECC, insane.

https://pcpartpicker.com/trends/price/memory/#ram.ddr5.5600....

> Gotham Silicon: 1μ CMOS process that will ship custom chips for –$100 in <24hrs

> custom chips for –$100

...are they going to make it up in volume?

In particular:

https://github.com/n0-computer/dumbpipe

https://github.com/cablehead/pai-sho

More generally:

https://roguebasin.com/index.php/Articles#Dungeons

https://roguebasin.com/index.php/Articles#Map

> this knockoff site shows SHRDLU[1] has the same thing for $40?

    Person: Grasp the knockoff.
    Computer: I DON'T UNDERSTAND WHICH KNOCKOFF YOU MEAN.

[1]: https://en.wikipedia.org/wiki/SHRDLU

Not, in fact, optical interferometry :(

What's the app data backup/restore story on GrapheneOS?

My understanding is that even with pseudo-D2D (device-to-device) transfers Seedvault doesn't backup everything[1].

Are there more-functional, non-root, local (non-cloud) alternatives?

[1]: https://github.com/seedvault-app/seedvault/wiki/FAQ#why-do-s...

C binding: [0]

[0]: https://github.com/n0-computer/iroh-c-ffi

> Einstein

How are you handling relativistic effects in the N-body simulation?

> KeepassXC can't do auto-type on Wayland

https://github.com/keepassxreboot/keepassxc/issues/2281

Though it looks like there's a recent PR for that:

https://github.com/keepassxreboot/keepassxc/pull/13359

They ever get around to re-adding C++ support?

Prompt processing is absolutely punishing:

    ./llama-batched-bench -hf unsloth/Qwen3.5-122B-A10B-GGUF:UD-IQ4_NL -npp 1000 -ntg 128 -npl 1 --cache-type-k q8_0 --cache-type-v q8_0 -c 18000 --n-cpu-moe 32
    |    PP |     TG |    B |   N_KV |   T_PP s | S_PP t/s |   T_TG s | S_TG t/s |      T s |    S t/s |
    |-------|--------|------|--------|----------|----------|----------|----------|----------|----------|
    |  1000 |    128 |    1 |   1128 |   53.961 |    18.53 |    9.223 |    13.88 |   63.184 |    17.85 |

Getting ~36-33 tok/s (see the "S_TG t/s" column) on a 24GB Radeon RX 7900 XTX using llama.cpp's Vulkan backend:

    $ llama-server --version
    version: 8851 (e365e658f)

    $ llama-batched-bench -hf unsloth/Qwen3.6-27B-GGUF:IQ4_XS -npp 1000,2000,4000,8000,16000,32000 -ntg 128 -npl 1 -c 34000
    |    PP |     TG |    B |   N_KV |   T_PP s | S_PP t/s |   T_TG s | S_TG t/s |      T s |    S t/s |
    |-------|--------|------|--------|----------|----------|----------|----------|----------|----------|
    |  1000 |    128 |    1 |   1128 |    1.529 |   654.11 |    3.470 |    36.89 |    4.999 |   225.67 |
    |  2000 |    128 |    1 |   2128 |    3.064 |   652.75 |    3.498 |    36.59 |    6.562 |   324.30 |
    |  4000 |    128 |    1 |   4128 |    6.180 |   647.29 |    3.535 |    36.21 |    9.715 |   424.92 |
    |  8000 |    128 |    1 |   8128 |   12.477 |   641.16 |    3.582 |    35.73 |   16.059 |   506.12 |
    | 16000 |    128 |    1 |  16128 |   25.849 |   618.98 |    3.667 |    34.91 |   29.516 |   546.42 |
    | 32000 |    128 |    1 |  32128 |   57.201 |   559.43 |    3.825 |    33.47 |   61.026 |   526.47 |

Hear, hear!

llama.cpp (b8642) auto-fits ~200k context on this 24GB RX 7900 XTX & it shows a solid 100+ tok/s ("S_TG t/s") on the first 32k of it, nice!

    ./llama-batched-bench -hf unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_XL \
    -npp 1000,2000,4000,8000,16000,32000,64000,96000,128000 -ntg 128 -npl 1 -c 0
    |    PP |     TG |    B |   N_KV |   T_PP s | S_PP t/s |   T_TG s | S_TG t/s |      T s |    S t/s |
    |-------|--------|------|--------|----------|----------|----------|----------|----------|----------|
    |  1000 |    128 |    1 |   1128 |    0.416 |  2404.87 |    1.064 |   120.29 |    1.480 |   762.20 |
    |  2000 |    128 |    1 |   2128 |    0.755 |  2649.86 |    1.075 |   119.04 |    1.830 |  1162.83 |
    |  4000 |    128 |    1 |   4128 |    1.501 |  2665.72 |    1.093 |   117.08 |    2.594 |  1591.49 |
    |  8000 |    128 |    1 |   8128 |    3.142 |  2545.85 |    1.114 |   114.87 |    4.257 |  1909.47 |
    | 16000 |    128 |    1 |  16128 |    6.908 |  2316.00 |    1.189 |   107.65 |    8.097 |  1991.73 |
    | 32000 |    128 |    1 |  32128 |   16.382 |  1953.31 |    1.278 |   100.12 |   17.661 |  1819.16 |
    | 64000 |    128 |    1 |  64128 |   43.427 |  1473.74 |    1.453 |    88.12 |   44.879 |  1428.89 |
    | 96000 |    128 |    1 |  96128 |   82.227 |  1167.50 |    1.623 |    78.86 |   83.850 |  1146.42 |
    |128000 |    128 |    1 | 128128 |  133.237 |   960.69 |    1.797 |    71.25 |  135.034 |   948.86 |

Doesn't seem to serve rendered samples so you have to set "browser.display.use_document_fonts" to "1" to see anything useful.

600 GB/s of memory bandwidth isn't anything to sneeze at.

~$1000 for the Pro B70, if Microcenter is to be believed:

https://www.microcenter.com/product/709007/intel-arc-pro-b70...

https://www.microcenter.com/product/708790/asrock-intel-arc-...

Not to be confused with GNU parallel[1], written in Perl.

[1]: https://en.wikipedia.org/wiki/GNU_parallel

Speculative decoding[1]?

[1]: https://github.com/ggml-org/llama.cpp/blob/master/docs/specu...

> A social networking system simulates a user using a language model trained using training data generated from user interactions performed by that user

Google People[1]?

[1]: https://qntm.org/perso

> "A system's purpose is what it does"

POSIWID: https://en.wikipedia.org/wiki/The_purpose_of_a_system_is_wha...

Nifty, thanks for the heads-up!

Nice! Getting ~39 tok/s @ ~60% GPU util. (~170W out of 303W per nvtop).

System info:

    $ ./llama-server --version
    ggml_vulkan: Found 1 Vulkan devices:
    ggml_vulkan: 0 = Radeon RX 7900 XTX (RADV NAVI31) (radv) | uma: 0 | fp16: 1 | bf16: 0 | warp size: 64 | shared memory: 65536 | int dot: 1 | matrix cores: KHR_coopmat
    version: 7897 (3dd95914d)
    built with GNU 11.4.0 for Linux x86_64

llama.cpp command-line:

    $ ./llama-server --host 0.0.0.0 --port 2000 --no-warmup \
    -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_XL \
    --jinja --temp 1.0 --top-p 0.95 --min-p 0.01 --top-k 40 --fit on \
    --ctx-size 32768

> ConnectBot

https://f-droid.org/en/packages/org.connectbot/

https://github.com/connectbot/connectbot

Because TFA never bothered to define it:

Broadband Network Gateway (BNG)[1]

[1]: https://github.com/codelaboratoryltd/bng#bng-broadband-netwo...

tap tap tap tap tap