s-zaizen/DeepSeek-V4-Flash-0731-Vision-NVFP4

DeepSeek-V4-Flash-Vision-Exp-NVFP4

This is a mixed-precision derivative of deepseek-ai/DeepSeek-V4-Flash-Vision-Exp at revision 86f746b36186f0e567729a5c06a8c918caba82a9.

Only the regular routed MoE experts are represented as NVFP4 W4A4 with group size 16. Attention, the router gate, shared experts, embeddings, the language model head, MTP/DSpark blocks, and the vision tower retain their source checkpoint formats.

The source expert weights are MXFP4. They are converted with NVIDIA ModelOpt's DeepSeek V4 lossless MXFP4-to-NVFP4 cast; activation input scales are calibrated with 64 samples from each of cnn_dailymail and nvidia/Nemotron-Post-Training-Dataset-v2, sequence length 512, MP=2 on two NVIDIA DGX Spark systems. The calibration-only tokenizer copy uses left padding, as recommended by ModelOpt; the published source tokenizer files remain unchanged. Model loading uses a tensor-at-a-time wrapper around the official PTQ entrypoint to avoid materializing a second 86 GB checkpoint in DGX Spark unified memory. For calibration on GB10 (SM121), the wrapper uses an isolated copy of the source inference code with the sparse-attention tile block reduced from 64 to 32: the source kernel requests 104,448 bytes of dynamic shared memory while GB10 permits 101,376 bytes. This calibration-only compatibility change does not modify the source or published inference files. ModelOpt is pinned to 029c67f27e67088fb19ac0a9af241dc2bc740650.

The source reference runtime also declares fast_hadamard_transform without a version constraint. Because that extension is absent from the pinned ARM64 runtime, the same isolated calibration copy supplies a normalized seven-stage PyTorch BF16 butterfly for the model's 128-wide indexer rotations. Its output is checked against the dense Walsh-Hadamard definition before calibration.

Status

• Structural validation: passed for all 48 shards.
• Lossless routed-expert weight cast: passed for 33024 tensors and 8657043456 NVFP4 blocks.
• Runtime support and generation validation: not yet claimed.
• Quality and throughput A/B: intentionally deferred until after publication.

Do not infer benchmark equivalence from the lossless weight cast alone: activation quantization remains a calibrated change and must be evaluated.

License

The source repository declares the MIT License. The original license and ancillary files are retained in this derivative.