convert : skip bias_vl tensor in DeepSeek-V4 DSpark conversion - #28294
Merged
Conversation
The DFLASH arch does not include FFN_EXP_PROBS_B_VL, so the DSpark conversion failed when it tried to write the mtmd-only hash routing tensor ffn.gate.bias_vl. Drop it like the tid2eid tensor; the DFLASH draft only consumes ffn.gate.bias via FFN_EXP_PROBS_B. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731
CISC
reviewed
Sep 3, 2026
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
CISC
approved these changes
Sep 3, 2026
4 tasks
fewtarius
pushed a commit
to fewtarius/CachyLLama
that referenced
this pull request
Sep 5, 2026
…org#28294) * convert : skip bias_vl tensor in DeepSeek-V4 DSpark conversion The DFLASH arch does not include FFN_EXP_PROBS_B_VL, so the DSpark conversion failed when it tried to write the mtmd-only hash routing tensor ffn.gate.bias_vl. Drop it like the tid2eid tensor; the DFLASH draft only consumes ffn.gate.bias via FFN_EXP_PROBS_B. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * cont : fix Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
thecodacus
pushed a commit
to thecodacus/llama.cpp
that referenced
this pull request
Sep 7, 2026
…org#28294) * convert : skip bias_vl tensor in DeepSeek-V4 DSpark conversion The DFLASH arch does not include FFN_EXP_PROBS_B_VL, so the DSpark conversion failed when it tried to write the mtmd-only hash routing tensor ffn.gate.bias_vl. Drop it like the tid2eid tensor; the DFLASH draft only consumes ffn.gate.bias via FFN_EXP_PROBS_B. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * cont : fix Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
x1250
pushed a commit
to x1250/llama.cpp
that referenced
this pull request
Sep 9, 2026
…org#28294) * convert : skip bias_vl tensor in DeepSeek-V4 DSpark conversion The DFLASH arch does not include FFN_EXP_PROBS_B_VL, so the DSpark conversion failed when it tried to write the mtmd-only hash routing tensor ffn.gate.bias_vl. Drop it like the tid2eid tensor; the DFLASH draft only consumes ffn.gate.bias via FFN_EXP_PROBS_B. Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 * cont : fix Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
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.
Overview
cont #28133 #28133 (comment)
Fix DSpark conversion for the new https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp.
GGUFs: https://huggingface.co/ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF
Requirements