Implement '--keep-split' to quantize model into several shards#6688
Merged
ggerganov merged 6 commits intoggml-org:masterfrom Apr 25, 2024
Merged
Implement '--keep-split' to quantize model into several shards#6688ggerganov merged 6 commits intoggml-org:masterfrom
ggerganov merged 6 commits intoggml-org:masterfrom
Conversation
Collaborator
|
Thanks. Do you mind to add a tests.sh as we did in #6655 |
Contributor
Author
|
@phymbert Done |
This comment was marked as off-topic.
This comment was marked as off-topic.
phymbert
reviewed
Apr 18, 2024
| LLAMA_LOG_INFO("%s: meta size = %zu bytes\n", __func__, meta_size); | ||
| auto weight = ml.get_weight(i); | ||
| struct ggml_tensor * tensor = weight->tensor; | ||
| if (weight->idx != (ctx_outs.size() - 1) && params->keep_split) { |
Collaborator
There was a problem hiding this comment.
I feel it not safe for future evolution as it assumes writing the tensors the same order they have been read. Could we simply check if weight->idx is not present in ctx_outs and retrieve ctx_out by tensor ?
Contributor
Author
There was a problem hiding this comment.
You are right. Then model splits writing should follow this logic to support case like "0 0 0 2 2 1 1". Besides, do you think incontinuous order should be considered like "0 0 0 2 1 2 1"?
ggerganov
reviewed
Apr 19, 2024
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
ggerganov
approved these changes
Apr 25, 2024
Seunghhon
pushed a commit
to Seunghhon/llama.cpp
that referenced
this pull request
Apr 26, 2026
…#6688) * Implement '--keep-split' to quantize model into several shards * Add test script * Update examples/quantize/quantize.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Split model correctly even if tensor id is out-of-order * Update llama_model_quantize_params * Fix preci failures --------- Co-authored-by: z5269887 <z5269887@unsw.edu.au> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
phuongncn
pushed a commit
to phuongncn/llama.cpp-gx10-dgx-sparks-deepseekv4
that referenced
this pull request
Apr 28, 2026
…#6688) * Implement '--keep-split' to quantize model into several shards * Add test script * Update examples/quantize/quantize.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Split model correctly even if tensor id is out-of-order * Update llama_model_quantize_params * Fix preci failures --------- Co-authored-by: z5269887 <z5269887@unsw.edu.au> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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.
Fix #6548
--keep-splitallowsquantizeto output shards instead of a full model. The number of shards depends on the input model files