ggml : dynamic ggml_sched_max_splits based on graph_size #9047
Conversation
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
github-actions
bot
added
the
ggml
slaren
reviewed
Aug 16, 2024
slaren
approved these changes
Aug 16, 2024
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Nov 15, 2024
* ggml : Dynamic ggml_sched_max_splits based on graph_size * Fixed and readded debug code for causes
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Nov 18, 2024
* ggml : Dynamic ggml_sched_max_splits based on graph_size * Fixed and readded debug code for causes
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
This fixes #9044
Sets ggml_sched_max_splits to be equal to graph_size as recommended by @slaren in #9044 (comment) since at most there is one split for each node in the graph.
Thanks to this change I was able to run GPU accelerated inference on BigLlama-3.1-681B-Instruct which prior to this change caused llama.cpp to crash.