[Model] Qwen3.5 support w/o vision, WIP#19456
Closed
pwilkin wants to merge 9 commits intoggml-org:masterfrom
Closed
[Model] Qwen3.5 support w/o vision, WIP#19456pwilkin wants to merge 9 commits intoggml-org:masterfrom
pwilkin wants to merge 9 commits intoggml-org:masterfrom
Conversation
CISC
reviewed
Feb 9, 2026
Comment on lines
+118
to
+126
| q = ggml_cont_4d(ctx0, ggml_permute(ctx0, q, 0, 2, 1, 3), S_k, n_tokens, H_k, n_seqs); | ||
| k = ggml_cont_4d(ctx0, ggml_permute(ctx0, k, 0, 2, 1, 3), S_k, n_tokens, H_k, n_seqs); | ||
| v = ggml_cont_4d(ctx0, ggml_permute(ctx0, v, 0, 2, 1, 3), S_v, n_tokens, H_v, n_seqs); | ||
| if (is_kda) { | ||
| g = ggml_cont_4d(ctx0, ggml_permute(ctx0, g, 0, 2, 1, 3), S_k, n_tokens, H_k, n_seqs); | ||
| } else { | ||
| g = ggml_cont_4d(ctx0, ggml_permute(ctx0, g, 2, 0, 3, 1), n_tokens, 1, H_k, n_seqs); | ||
| } | ||
| beta = ggml_cont(ctx0, ggml_permute(ctx0, beta, 2, 0, 1, 3)); |
CISC
reviewed
Feb 9, 2026
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Collaborator
Author
|
@ggerganov tested on MXFP4 quant for Coder-Next: |
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Member
|
I think the unification of the delta net implementations should be done separately from Qwen3.5 - likely in #18792. I think this will likely take longer than Qwen3.5 release, so it's better to add Qwen3.5 support without basing the implementation on that branch. |
Collaborator
Author
|
@ggerganov okay, I'll do it on master. |
Collaborator
Author
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Followup to #19435
Rebased on top of #18792 together with @ngxson 's fix for chunking.