| # OpenMOSS-Team/MOSS-VL-Realtime-FP8 | |
| - Runtime: Transformers `online_generate` / `create_realtime_session`. | |
| - Weights: compressed-tensors FP8 E4M3 on 252 self-attention/MLP Linear layers. | |
| - Activations: FP8 per-token dynamic on the same 252 Linear inputs. | |
| - BF16: cross-attention layers, vision encoder/merger, embeddings, norms and `lm_head`. | |
| - KV cache: Transformers HQQ INT8, group size 64, residual length 128. | |
| - Attention backend: `flash_attention_2`. | |