UPSTREAM PR #16490: graph : reuse SSM graphs #133
Closed
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
DajanaV
had a problem deploying
to
PROD__AL_DEMO
GitHub Actions
Failure
DajanaV
force-pushed
the
main
branch
24 times, most recently
from
98e1e20 to
2791104
Compare
DajanaV
force-pushed
the
main
branch
19 times, most recently
from
24733fb to
4b4bb7c
Compare
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Outdated suggestions cannot be applied.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.
Mirrored from ggml-org/llama.cpp#16490
Not sure if there is a reason not to enable graph reuse for recurrent graphs (mamba, hybrids, SSM, etc.). Did a few tests and seems to work, resulting in some modest perf improvements. cc @gabe-l-hart @compilade
Without graph reuse
make -j && LLAMA_GRAPH_REUSE_DISABLE=1 ./bin/llama-bench -m ../models/mamba-130m/ggml-model-f16.gguf -m ../models/granite-4-h-tiny/ggml-model-q8_0.gguf -m ../models/ai21-jamba-mini-1.7/ggml-model-q8_0.gguf -m ../models/liquidai-lfm2-2.6b/ggml-model-q4_k.gguf -fa 1 -t 1 -n 32With graph reuse
make -j && ./bin/llama-bench -m ../models/mamba-130m/ggml-model-f16.gguf -m ../models/granite-4-h-tiny/ggml-model-q8_0.gguf -m ../models/ai21-jamba-mini-1.7/ggml-model-q8_0.gguf -m ../models/liquidai-lfm2-2.6b/ggml-model-q4_k.gguf -fa 1 -t 1 -n 32