Search
5 results for “tg9541”
-
I've been testing the new llama-server 1.0.0 release: the MoE optimizations really work well for my dual RTX 3060 machine: with Gemma-4-26b-a4b I get up to 90 tokens/s for small context sizes, a 20% speed-up.
But that's not all: MTP works very well, and I get up to 130 tokens/s (small context) and still > 90 token/s for larger ones.
-
RE: https://mastodon.sdf.org/@larsbrinkhoff/117613250258413934
The process of keeping historical systems alive tells us something about the nature of resilience:
this is the result of a laudable personal commitment to preservation and curation in multiple fields, including the re-implementation of 1970s computer logic on hardware available today.
Congrats!