| 123456789101112131415 |
- # Dense linears the checkpoint left in bf16 (dense_fp8.py): FP8, except the
- # layers matching VLLM_DENSE_W4, which go to NVFP4 (megadense4.cu): by default
- # the KDA in_proj, attention o_proj, the shared experts and every DFlash
- # drafter layer. Needs snapshot.yaml's loader;
- # keeps its own snapshots.
- services:
- glm53:
- volumes:
- - ../experimental/snapshot/dense_fp8.py:/usr/local/lib/python3.12/dist-packages/vllm/model_executor/model_loader/dense_fp8.py:ro
- - ../experimental/megamoe/megadense4.cu:/opt/megamoe/megadense4.cu:ro
- environment:
- - VLLM_DENSE_FP8=1
- - VLLM_DENSE_FP8_LM_HEAD=${VLLM_DENSE_FP8_LM_HEAD:-1}
- - VLLM_DENSE_W4=${VLLM_DENSE_W4:-in_proj_qkvbfg_a$$|^model\.|self_attn\.o_proj$$|shared_experts\.(gate_up_proj|down_proj)$$}
- - VLLM_WEIGHT_SNAPSHOT_TAG=fp8w4c-2026-09-28
|
