Open
Conversation
Add new kimi-k2.5 keys to mtmd convert Update V_MMPROJ tensor mapping for new mm_projector.proj keys Update V_M_IMP_NORM for new mm_projector.pre_norm key
loci-dev
temporarily deployed
to
PROD__AL_DEMO
GitHub Actions
Inactive
|
Based on the analysis, no functions were identified with meaningful performance changes between the base and target versions. The function_insights_topk tool returned empty results for both response time and throughput time metrics, indicating that the code changes in this version do not introduce measurable performance impacts. This suggests that the modifications between versions are either:
Conclusion: No performance regression or improvement was detected. The changes appear performance-neutral from a static analysis perspective. See the complete breakdown in Version Insights |
loci-dev
force-pushed
the
main
branch
25 times, most recently
from
96d29ac to
dbad616
Compare
loci-dev
force-pushed
the
main
branch
30 times, most recently
from
5330dfe to
ff4fb1d
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Mirrored from ggml-org/llama.cpp#19170
Adding support for https://huggingface.co/moonshotai/Kimi-K2.5
Since this model includes compressed-tensors (INT4 for the conditional experts), I moved the
dequant_modelto theprepare_tensorscall at @compilade's suggestion. The model conversion fails otherwise because thequantization_configis nested under thetext_configin the config.json.Additionally, this model adds some new keys for the vision tower, prefixed as
vt_, and the preprocessor_config.json has the expected fields nested in themedia_proc_cfgkey.This PR does not include the "hacked" Q4_0 changes by @jukofyork, referred to in this comment.
While the
mmprojconversion appears to work and the model loads and can decode images, I've got some weird output when using the vision component that leads me to believe there is a conversion issue somewhere or some other missing component. I think I need some review from @ngxson to help get it working correctly.