Converted DeepSeek-V4-Flash-0731 weights for deployment on NVIDIA A100 / A800 (SM80) GPUs. > For deployment configuration, installation steps, launch scripts and benchmarks, see: > GitHub: yobo2u/DeepSeek-V4-Flash-0731-A100 > SM90+ users (H100 / H800 / H20) should use the official upstream weights directly — this repository is not needed. The SM80 architecture used by A100/A800 does not support the native FP8 execution path that the original model targets on newer GPUs. The weights in this repository were converted offline so they can run on SM80 GPUs together with a dedicated SGLang 0.5.16 monkeypatch: — Non-expert weights: converted to BF16 — MoE expert weights: kept in MXFP4 — Shards: 48 safetensors files — Total size: approximately 173 GB (decimal) — Context length: up to 1,048,576 tokens — Recommended inference framework: SGLang 0.5.16 — Recommended hardware: 8× A100 80GB or 8× A800 80GB, TP=8 — Speculative decoding: DSpark supported Th The full runtime environment, pinned versions, monkeypatch source, launch arguments and benchmark scripts are maintained in the GitHub configuration repository. Do not reuse launch commands…
Модальности:
Генерация текста
Задача: Генерация текста
Автор: yobo2u
Теги: deepseek_v4, deepseek, deepseek-v4, a100, a800, sm80, sglang, dspark
Лайков: 4 | Загрузок: 400
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
