09-20-2026, 08:24 AM
Appreciate the detail. That matches what I saw on A6000. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
trying not to rebuild again
|
eval setup for local models with TensorRT-LLM
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
eval setup for local models with TensorRT-LLM - by sparrowworks88 - 09-20-2026, 07:33 AM
Re: eval setup for local models with TensorRT-LLM - by batchpeak - 09-20-2026, 08:24 AM
Re: eval setup for local models with TensorRT-LLM - by cacheline - 09-23-2026, 12:36 PM
Re: eval setup for local models with TensorRT-LLM - by deltastation - 09-20-2026, 09:18 AM
Re: eval setup for local models with TensorRT-LLM - by northgrid33 - 09-23-2026, 10:03 AM
Re: eval setup for local models with TensorRT-LLM - by kernelarch - 09-23-2026, 01:00 PM
Re: eval setup for local models with TensorRT-LLM - by phaseport36 - 09-24-2026, 01:16 PM
Re: eval setup for local models with TensorRT-LLM - by localtinker - 09-25-2026, 01:17 PM
|
Users browsing this thread: 1 Guest(s)