#2149 [Bug] v0.1.43 release broke Strata on AMD 7000 series card. Weights loaded to VRAM get offloaded to RAM after a few seconds.

open · @PARLTOR · 0 comentarios · En GitHub

Setup & install AMD / HIP Models & quants

Descripción

v0.1.43 release broke Strata on AMD 7000 series card. Weights loaded to VRAM get offloaded to RAM after a few seconds. Leading RAM usage to spike until limit (64Gb in my case) => blue screen, sluggish, etc.

Clean re-install of latest release v0.1.43 => same behavior across IQ3_xxs and IQ3_s. Across the different context length options and KV quantization choices.

7900 XTX 24Gb on Win11

Was working well and v0.1.41 and previous

En el sitio

Install Strata
Model sizes & RAM
Release notes

Enlaces a install, modelos, releases.