Conversation
- Adapt existing L40s inference tutorial for Ubuntu 26.04 LTS - Document CUDA 13.1 + GCC 15 incompatibility and patch fix - Use cuda-toolkit-13 instead of nvidia-cuda-toolkit - Specify gcc-14/g++-14 for CUDA host compiler - Note: tested and verified build on running Ubuntu 26.04 instance
This reverts commit 37253e5.
Set timezone to Europe/Oslo for log consistency. Add nload for real-time network monitoring. Both apply to Ubuntu 24 and 26 sections.
- Add python3.14-venv to apt install (required for python3 -m venv) - Replace deprecated --no-mmap with --load-mode mmap - Add measured benchmarks from actual L40S run - Clarify that cmake flags alone cannot fix NVML/GCC issues WHY: After testing on the actual L40S vGPU instance, two pre-build fixes (NVML symlink + math_functions.h patch) are mandatory regardless of cmake flags. The tutorial was also updated with real benchmark data (MTP: 200 t/s, 100% draft acceptance) and the --no-mmap deprecation warning from llama.cpp.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.