# Upstream provenance — DeepSeek-V4-Flash-Vision-Exp recipe

Day-0 port of the multimodal lane:

- repo:   https://github.com/sfxnz/DeepSeek-V4-Flash-Vision-Exp-vLLM-2x-DGX-Spark
- commit: 7a958128b84a (2026-08-31)
- license: repo LICENSE (see tree); model deepseek-ai/DeepSeek-V4-Flash-Vision-Exp is MIT;
  model revision served: 86f746b36186f0e567729a5c06a8c918caba82a9

| local file                | upstream path                          |
|---------------------------|----------------------------------------|
| Dockerfile                | docker/Dockerfile.b12x-vision (FROM genericized to ARG BASE_IMAGE; original pins eugr/spark-vllm-b12x:latest, digest sha256:7dc02f162929943ba2e14514066ed2a04bb7e9ed3592d4eb460ebcbb1f8376bd) |
| patch_dspark_skip_bias_vl.py | docker/patch_dspark_skip_bias_vl.py (verbatim) |
| plugin/dsv4_vision/*      | docker/plugin/dsv4_vision/* (verbatim; registered as VLLM_PLUGINS=dsv4_vision via the vllm.general_plugins entry point) |
| build.sh, versions.env    | ours (generic driver; BASE_IMAGE/TAG overridable for the eugr-vs-aidendle94 fork comparison) |

Known upstream limitations (their README): image-token expert routing in the
MoE router is not wired for the ViT lane yet (`ffn.gate.bias_vl` gate
tensors are skipped by the loader patch); text decode unaffected.
VLLM_USE_B12X_MHC must stay OFF (this checkpoint's rms_norm_eps is 1e-20;
the fused Gram mHC kernel only accepts 1e-6).