deepseek kind of innovated on this using off-the-shelf components right ?
to quote from their paper
"In order to ensure sufficient computational performance for DualPipe, we customize efficient
cross-node all-to-all communication kernels (including dispatching and combining) to conserve
the number of SMs dedicated to communication. The implementation of the kernels is codesigned with the MoE gating algorithm and the network topology of our cluster."
the Qualcomm Adreno 750 GPU is a Snapdragon Gen 3 device. This is basically an android device.
I wonder why Valve is maintaining a separate linux and driver fork for this. Snapdragon Gen 3 android game SDK works very well...including Windows emulation. https://www.youtube.com/watch?v=-hsQ_-8HV6g
not saying what Valve is doing is not spectacular. But i cant help but wonder if it isnt a more productive use of their resources to mainline this in Android ?
Maybe even accelerate the Desktop Android merge (which Qualcomm is pushing ! https://www.theverge.com/news/784381/qualcomm-ceo-seen-googl...)
Android that is Valve compatible will further Valve's goals of open platforms than maintaining their own fork.
If you want to "accelerate the Desktop Android merge" you need devices to be properly supported in the mainline kernel and Mesa stack, which is what everyone uses on desktop. This is what Valve is doing. Google may be merging Android and ChromeOS, but even ChromeOS is far from a true "desktop"-class OS.
this is pretty cool!
have you found success with image editing in nano banana - i mean photoshop-like stuff.
from your article i seem to wonder if nano banana is good for editing versus generating new images.
That IS the use-case for Nano Banana (as opposed to pure generative like Imagen4).
In my benchmarks, Nano-Banana scores a 7 out of 12. Seedream4 managed to outpace it, but Seedream can also introduce slight tone mapping variations. NB is the gold standard for highly localized edits.
Comparisons of Seedream4, NanoBanana, gpt-image-1, etc.
I tried your "Remove all the brown pieces of candy from the glass bowl." prompt against Nano Banana Pro and it converted them to green, which I think is a pass by your criteria. Original Nano Banana had failed that test because it changed the composition of the M&Ms.
Thanks Simon - I'm in the middle of re-running all my prompts through NB Pro at the moment. Nice to know it's already edged out the original. It also passed the SHRDLU test (swapping colored blocks) without cheating and just changing the colors. I'll have an update to the site shortly!
EDIT: Finished the comparisons. NB Pro scored a few more points than NB which was already super impressive.
Thanks for the comment! I will look into this since I certainly think the ideal scenario would be the core mermaid project supporting customizations in their engine. I imagine that before that I would have to refine the project further after which it would be interesting to see if they would be open to supporting it!
did decently (but not in top 10). I got a lot of the same linkedin comments with "we even gave you some reviews for free to show we are serious". Said no to them and that turned into retribution.
started getting negative comments https://postimg.cc/n9tDDB0S . had to stay up all night to reply to negative comments with link to my github showing the source :(
for some reason they all deleted themselves (or got removed). not sure.
you folks should really try the lenovo yoga series. especially this year's yoga slim aura edition (which has the intel lunar lake chips). The ipex-llm extensions are fairly stable and work very well ( https://github.com/intel/intel-extension-for-pytorch )
and the build quality of the laptop is exactly like the macbook air - i have both.
The discussion is mostly around battery life. How's the battery life on your Yoga, how much power does it lose on standby, and what operating system do you use?
windows.
all day battery life. holds up pretty well to the macbook air 15 at similar workloads. macbook does get 1-1.5 hour more battery life.
The lunar lake is an insane chip.
to quote from their paper "In order to ensure sufficient computational performance for DualPipe, we customize efficient cross-node all-to-all communication kernels (including dispatching and combining) to conserve the number of SMs dedicated to communication. The implementation of the kernels is codesigned with the MoE gating algorithm and the network topology of our cluster."
reply