Update build.yml, enable rpc for windows cuda builds #9184
Merged
Conversation
This file contains 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
build rpc-server for windows cuda
github-actions
bot
added
the
devops
ggerganov
approved these changes
Aug 26, 2024
mofosyne
added
the
Review Complexity : Low
4 tasks
|
Looks good to me. Also feel free to file an issue with the model which didn't work with the RPC backend. |
dsx1986
pushed a commit
to dsx1986/llama.cpp
that referenced
this pull request
Oct 29, 2024
build rpc-server for windows cuda
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
enable rpc for windows cuda builds
The current windows cuda build's llama-server ignores --rpc arguments, and it does not build cuda enabled rpc-server.
I have tested several models, with 1 llama-server and 1 remote rpc-server, most models work, only one mixtral q4km quant crashes with
ggml/src/ggml-rpc.cpp:893: GGML_ASSERT(tensor->data + tensor_size >= tensor->data) failed
I think it should be fine to build rpc enabled cuda llama-server and cuda enabled rpc-server by default.