|
when TensorRT-LLM clearly wins
|
10-16-2026, 01:27 PM
Interesting, I hadn't tried that. The pattern around token cost has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
If you post your exact settings, people here can probably narrow it down pretty fast.
serving stack tinkerer
|
|
« 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
|
