expose n_gpu_layers parameter of llama.cpp #1890
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
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
cebtenzzre
force-pushed
the
cfg-gpu-layers
branch
from
823840d
to
3189617
Compare
manyoso
approved these changes
Jan 30, 2024
manyoso
approved these changes
Jan 31, 2024
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Leaving ChatLLM instances around at exit time means global destructors start running while m_llmThread instances are still running llama.cpp code. Explicitly destroy these before exit to prevent a heap-use-after-free. Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
cebtenzzre
force-pushed
the
cfg-gpu-layers
branch
from
1327623
to
c9b969e
Compare
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
dpsalvatierra
pushed a commit
to dpsalvatierra/gpt4all
that referenced
this pull request
Feb 16, 2024
Also dynamically limit the GPU layers and context length fields to the maximum supported by the model. Signed-off-by: Jared Van Bortel <jared@nomic.ai>
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Outdated suggestions cannot be applied.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.
This is the minimal implementation of configurable per-model partial offloading. It is up to the user to know/figure out how many layers the model has, and how many they can to load into VRAM without running out.