|
TensorRT-LLM worth the setup time with SGLang
|
10-11-2026, 05:54 AM
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at KV cache pressure. Once you know the plain path works, then add the faster path back in piece by piece.
I'm happy to test one more variant if you want a second data point. |
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
TensorRT-LLM worth the setup time with SGLang - by torchshed66 - 10-09-2026, 05:28 PM
Re: TensorRT-LLM worth the setup time with SGLang - by macrotinker - 10-11-2026, 05:54 AM
Re: TensorRT-LLM worth the setup time with SGLang - by northcraft90 - 10-12-2026, 06:36 PM
Re: TensorRT-LLM worth the setup time with SGLang - by northgrid33 - 10-12-2026, 07:45 PM
Re: TensorRT-LLM worth the setup time with SGLang - by routecrate - 10-12-2026, 08:21 PM
Re: TensorRT-LLM worth the setup time with SGLang - by macrotinker - 10-12-2026, 08:56 PM
Re: TensorRT-LLM worth the setup time with SGLang - by kernelgrid - 10-13-2026, 01:13 AM
|
