DeepSeek Models
DeepSeek is a primary KTransformers model family for both inference and SFT. Inference and fine-tuning use different methods and package paths, so their statuses are listed separately.
Inference
| Model | Entry | Method | Status |
|---|---|---|---|
| DeepSeek V4-Flash | kt run deepseek-v4-flash | MXFP4 | Needs smoke; narrow path. |
| DeepSeek V3.2 | kt run deepseek-v3.2 or manual tutorial | Registry uses FP8; older tutorial uses AMXINT4 | Needs reconciliation and smoke. |
| DeepSeek V3-0324 / R1-0528 | kt run deepseek-v3 / kt run deepseek-r1 | Registry default AMXINT4 | Current / Needs docs. |
Fine-Tuning
Use DeepSeek SFT. DeepSeek V3 public checkpoints may be FP8, but current KT SFT uses AMXBF16, AMXINT8, or AMXINT4, not native FP8 SFT.
Source Material
Relevant GitHub sources:
doc/en/DeepSeek-V4-Flash.mddoc/en/kt-kernel/deepseek-v3.2-sglang-tutorial.mddoc/en/SFT/KTransformers-Fine-Tuning_Quick-Start.mddoc/en/SFT/KTransformers-Fine-Tuning_User-Guide.md