09-17-2026, 10:57 PM
I think the bottleneck is somewhere else. I get why that seems right, but on 7900 XTX the bottleneck felt elsewhere. Worth testing the simpler explanation before adopting the more interesting one.
Inference
›
Prompting & Context Engineering
›
Prompts / System Prompts
few-shot when you actually need it with PyTorch
few-shot when you actually need it with PyTorch
|
few-shot when you actually need it with PyTorch
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
few-shot when you actually need it with PyTorch - by promptspark58 - 09-16-2026, 04:03 AM
Re: few-shot when you actually need it with PyTorch - by mlxgarden - 09-16-2026, 04:30 AM
Re: few-shot when you actually need it with PyTorch - by phasescope - 09-16-2026, 05:38 AM
Re: few-shot when you actually need it with PyTorch - by promptspark58 - 09-17-2026, 06:07 AM
Re: few-shot when you actually need it with PyTorch - by mlxgarden - 09-17-2026, 02:37 PM
Re: few-shot when you actually need it with PyTorch - by northgarden37 - 09-17-2026, 10:57 PM
Re: few-shot when you actually need it with PyTorch - by nanopatch - 09-19-2026, 01:31 AM
Re: few-shot when you actually need it with PyTorch - by cobalttinker - 09-18-2026, 10:58 PM
Re: few-shot when you actually need it with PyTorch - by localpatch - 09-19-2026, 02:08 PM
|
Users browsing this thread: 1 Guest(s)