HackerLangs
トップ新着トレンドコメント過去質問紹介求人

GrayShade

no profile record

投稿

S8102A: Requiring internet-enabled devices to conduct age assurance

nysenate.gov
1 ポイント·投稿者 GrayShade·4 か月前·1 コメント

Privacy Preserving DNS Telemetry in Debian PHP Packages

salsa.debian.org
1 ポイント·投稿者 GrayShade·5 か月前·1 コメント

コメント

GrayShade
·先月·議論
On systemd, you can use ~/.config/environment.d to set it. Don't rely on your shell.
GrayShade
·2 か月前·議論
Fedora is patched.
GrayShade
·3 か月前·議論
I get 20 t/s on the UD-Q6_K_XL quant, Radeon 6800 XT.
GrayShade
·3 か月前·議論
It only supports CUDA on Linux.
GrayShade
·3 か月前·議論
You can, after you unlock it.
GrayShade
·3 か月前·議論
We've had shitty bloated websites before LLMs were a thing.
GrayShade
·3 か月前·議論
It's plain FUD. systemd always had fields for the full name, email address and location. They were optional, just like the date of birth. Bad systemd!
GrayShade
·3 か月前·議論
The operating system does not need to know your full name, email and location in order to manage your hardware and software, yet systemd has had optional fields for those for years and nobody complained. They added an extra optional field for the date of birth.

> Some of this has been fueled by a misinformation campaign that has targeted the systemd project and Taylor specifically, resulting in Taylor being doxxed and receiving death threats.

I see.
GrayShade
·4 か月前·議論
It's easier to torrent stuff than to get 4K in Netflix on Linux.
GrayShade
·4 か月前·議論
1.82.7 doesn't have litellm_init.pth in the archive. You can download them from pypi to check.

EDIT: no, it's compromised, see proxy/proxy_server.py.
GrayShade
·4 か月前·議論
It's gone: https://github.com/bjarneo/cliamp/commit/085734a86343a80176d...
GrayShade
·4 か月前·議論
Don't forget location.
GrayShade
·4 か月前·議論
It doesn't, and it's optional.
GrayShade
·4 か月前·議論
Looks like it's a bit slower today. Running llama.cpp b8192 Vulkan.

$ ./llama-cli unsloth_Qwen3.5-35B-A3B-GGUF_Qwen3.5-35B-A3B-UD-Q4_K_XL.gguf -c 65536 -p "Hello"

[snip 73 lines]

[ Prompt: 86,6 t/s | Generation: 34,8 t/s ]

$ ./llama-cli unsloth_Qwen3.5-35B-A3B-GGUF_Qwen3.5-35B-A3B-UD-Q4_K_XL.gguf -c 262144 -p "Hello"

[snip 128 lines]

[ Prompt: 78,3 t/s | Generation: 30,9 t/s ]

I suspect the ROCm build will be faster, but it doesn't work out of the box for me.
GrayShade
·4 か月前·議論
That's not a shell, it's a Python interpreter compiled to WASM and running in the browser.
GrayShade
·4 か月前·議論
This feels a bit pessimistic. Qwen 3.5 35B-A3B runs at 38 t/s tg with llama.cpp (mmap enabled) on my Radeon 6800 XT.
GrayShade
·4 か月前·議論
And footnote 3 is unreferenced.
GrayShade
·4 か月前·議論
It did, there's two incompatible approaches, zram and zswap.
GrayShade
·4 か月前·議論
The Signal device linking feature is just as fast. It's partly a trick -- it will look for QR codes even outside the central area, so under good conditions it can get a read before you even get a rough orientation.
GrayShade
·5 か月前·議論
Maybe that's the only API-visible change, saying nothing about the actual capabilities of the model?