What hardware do you have? I’ve been playing with a 258V and OpenVINO has come a longggggg way.
peddling-brink 12 hours ago [-]
Two arc b60s. The intel vllm build is getting me ~15t/s decode with heavy context using qwen3.8 27b.
bitexploder 15 minutes ago [-]
Those cards should be able to do a lot more. They support int8 and they have very good processing speed. For reference I have a single V100 running around 900t/s prefill and 100 t/s decode during DeepSWE runs on 27B (4 bit quant). Those cards have half the bandwidth so a realistic decode is going to stop around 50 t/s, but those cards can support NVFP4 more easily than the V100. Combined with a TP build you should be able to get 100 t/s. And you should be able to 2x the prefill of a V100. I have had Claude optimizing llama.cpp for about a week and am at around 300 t/s decode so far on two ancient V100s @ 64 GB RAM.
Also for the 3 people that ever read this and are curious about local models still, Qwen 27B 3.8 matched Sonnet 5 in the 17 DeepSWE tasks I have run so far, solving the exact same 7 it has. Caveat: datacurve combined low/medium/high Sonnet 5 data.
ContinuityLab 3 hours ago [-]
[dead]
shayanjavadi 15 hours ago [-]
[dead]
dlcarrier 16 hours ago [-]
From what I've seen, Vulkan adds a lot of overhead on Intel hardware.
gunalx 8 hours ago [-]
Yes and no. I tested llamacpp on my intel gpu with both vulkan and sycl. I measured them to be in the same ballpark even if i have se en pepole claim marger differences than i observed.
In the end i took the sligth slowdown of vulkan to have a more stable and higher development velocity backend
While being able to use identical setups on both intel and and gpus.
Rendered at 14:42:15 GMT+0000 (UTC) with Wasmer Edge.
I got excited about someone paying attention to intel. Oh well.
https://github.com/ggml-org/llama.cpp/blob/master/docs/backe...
Also for the 3 people that ever read this and are curious about local models still, Qwen 27B 3.8 matched Sonnet 5 in the 17 DeepSWE tasks I have run so far, solving the exact same 7 it has. Caveat: datacurve combined low/medium/high Sonnet 5 data.
In the end i took the sligth slowdown of vulkan to have a more stable and higher development velocity backend While being able to use identical setups on both intel and and gpus.