[router] add base_gpu_id server args & merged radix tree python reference #2115
+513
−2
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Outdated suggestions cannot be applied.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.
Motivation
This PR prepares for #2114 by:
Adding
base_gpu_id
server argument to set the device ID offset when starting TP server. This enables starting multiple TP servers with different base GPU IDs when launching several servers and the router together using a single command. This also eliminates the need of settingCUDA_VISIBLE_DEVICE
if we want to launch on certain GPUsAdding merged radix tree Python implementation. This serves as an experimental Python version which I referenced for my Rust implementation.
Modifications
Checklist