|
when TensorRT-LLM clearly wins
|
10-15-2026, 12:22 AM
Quote:Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt? Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.
Mostly CUDA, sometimes wrong, usually measured
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
when TensorRT-LLM clearly wins - by macrotinker - 10-12-2026, 03:34 AM
Re: when TensorRT-LLM clearly wins - by kernelmike - 10-13-2026, 03:50 PM
Re: when TensorRT-LLM clearly wins - by vramscope - 10-14-2026, 04:07 PM
Re: when TensorRT-LLM clearly wins - by kernelgrid - 10-14-2026, 09:52 PM
Re: when TensorRT-LLM clearly wins - by kernelmike - 10-14-2026, 05:20 PM
Re: when TensorRT-LLM clearly wins - by kernelmike - 10-15-2026, 12:22 AM
Re: when TensorRT-LLM clearly wins - by syshouse - 10-16-2026, 12:57 AM
Re: when TensorRT-LLM clearly wins - by audioforge - 10-16-2026, 01:27 PM
Re: when TensorRT-LLM clearly wins - by pixelcrate82 - 10-16-2026, 02:28 PM
|
