Files
llama.cpp/conversion
Georgi Gerganov d646c9d155 convert : skip bias_vl tensor in DeepSeek-V4 DSpark conversion (#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>
2026-09-03 10:37:23 +03:00
..
2026-09-02 12:46:16 +02:00
2026-08-17 10:15:11 +02:00