Closed DreamGenX closed 2 months ago
@QiJune @kaiyux Can you comment on this question?
@DreamGenX please refer to https://nvidia.github.io/TensorRT-LLM/performance/perf-best-practices.html
@nv-guomingz Thank you, but I have read that guide, and that's about arguments for trtllm-build
. The snipped from above is about building the library from source, so I was curious about that:
Building from source code is necessary if you want the best performance https://nvidia.github.io/TensorRT-LLM/installation/build-from-source-linux.html
@Shixiaowei02 , would u please add comments here? is there any potential perf improvement introduced by building from the source code ?
This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 15 days."
This issue was closed because it has been stalled for 15 days with no activity.
In the guide it says:
I have a custom serving stack that requires me to build from source, and would like to understand what sort of performance knobs / benefits are available at build time.