On the SDK front, you tried just having an agent reimplement the model you're interested in and just use the weights? I've taken to treating off the shelf implementations as reference implementations anyway, because I can often squeeze out significantly better performance for my configuration and use case by having Codex hammer at it for a few hours.

▲

sroussey 4 hours ago | parent | next [-]

Hugging face is working on something like this where well known models get fused into a single implementation.

▲

drivebyhooting 4 hours ago | parent | prev [-]

Could you share the prompts and workflow? I’ve tried this too, but with mixed success when it comes to creating custom tile kernels.

I would really appreciate your input!

	▲	mistercow 4 hours ago \| parent [-]
		It's been pretty ad hoc, but my prompts are nothing special. Things I generally do: 1. Top end model on high/xhigh thinking (last time I did it it was Sol xhigh I think) 2. Make sure it creates some representative fixtures of different sizes and sets up a good testing, profiling and benchmarking loop that doesn't require my input. 3. Make sure it has access to reference implementation code Edit: Oh and one obvious pitfall that for some reason I still have to remind even smart models of from time to time: make sure it knows not to try to parallelize its benchmark runs. I've occasionally had an agent struggle to figure out absolutely nonsensical data because it tried to run multiple tests on the same compute hardware simultaneously.