lukealonso's picture
Publish step-5500 QAD with MXFP8 attention and NVFP4 MTP experts
6909a5b verified
Raw History Blame Contribute Delete
14.6 kB
{
"trunk": "local-inference-lab/Qwen3.8-Flash-Next-NVFP4@60215d26cf5e42c2db6128774032d57fc62678da",
"attention_and_mtp_experts_from": "local-inference-lab/Qwen3.8-Flash-Next-NVFP4@7c4f1bc1a2d6847e0cbc01ac6b823f00251de8dd",
"replaced_modules": [
"model.language_model.layers.0.linear_attn.in_proj_a",
"model.language_model.layers.0.linear_attn.in_proj_b",
"model.language_model.layers.0.linear_attn.in_proj_qkv",
"model.language_model.layers.0.linear_attn.in_proj_z",
"model.language_model.layers.0.linear_attn.out_proj",
"model.language_model.layers.1.linear_attn.in_proj_a",
"model.language_model.layers.1.linear_attn.in_proj_b",
"model.language_model.layers.1.linear_attn.in_proj_qkv",
"model.language_model.layers.1.linear_attn.in_proj_z",
"model.language_model.layers.1.linear_attn.out_proj",
"model.language_model.layers.10.linear_attn.in_proj_a",
"model.language_model.layers.10.linear_attn.in_proj_b",
"model.language_model.layers.10.linear_attn.in_proj_qkv",
"model.language_model.layers.10.linear_attn.in_proj_z",
"model.language_model.layers.10.linear_attn.out_proj",
"model.language_model.layers.11.self_attn.indexer.index_qk_proj",
"model.language_model.layers.11.self_attn.k_proj",
"model.language_model.layers.11.self_attn.o_proj",
"model.language_model.layers.11.self_attn.q_proj",
"model.language_model.layers.11.self_attn.v_proj",
"model.language_model.layers.12.linear_attn.in_proj_a",
"model.language_model.layers.12.linear_attn.in_proj_b",
"model.language_model.layers.12.linear_attn.in_proj_qkv",
"model.language_model.layers.12.linear_attn.in_proj_z",
"model.language_model.layers.12.linear_attn.out_proj",
"model.language_model.layers.13.linear_attn.in_proj_a",
"model.language_model.layers.13.linear_attn.in_proj_b",
"model.language_model.layers.13.linear_attn.in_proj_qkv",
"model.language_model.layers.13.linear_attn.in_proj_z",
"model.language_model.layers.13.linear_attn.out_proj",
"model.language_model.layers.14.linear_attn.in_proj_a",
"model.language_model.layers.14.linear_attn.in_proj_b",
"model.language_model.layers.14.linear_attn.in_proj_qkv",
"model.language_model.layers.14.linear_attn.in_proj_z",
"model.language_model.layers.14.linear_attn.out_proj",
"model.language_model.layers.15.self_attn.indexer.index_qk_proj",
"model.language_model.layers.15.self_attn.k_proj",
"model.language_model.layers.15.self_attn.o_proj",
"model.language_model.layers.15.self_attn.q_proj",
"model.language_model.layers.15.self_attn.v_proj",
"model.language_model.layers.16.linear_attn.in_proj_a",
"model.language_model.layers.16.linear_attn.in_proj_b",
"model.language_model.layers.16.linear_attn.in_proj_qkv",
"model.language_model.layers.16.linear_attn.in_proj_z",
"model.language_model.layers.16.linear_attn.out_proj",
"model.language_model.layers.17.linear_attn.in_proj_a",
"model.language_model.layers.17.linear_attn.in_proj_b",
"model.language_model.layers.17.linear_attn.in_proj_qkv",
"model.language_model.layers.17.linear_attn.in_proj_z",
"model.language_model.layers.17.linear_attn.out_proj",
"model.language_model.layers.18.linear_attn.in_proj_a",
"model.language_model.layers.18.linear_attn.in_proj_b",
"model.language_model.layers.18.linear_attn.in_proj_qkv",
"model.language_model.layers.18.linear_attn.in_proj_z",
"model.language_model.layers.18.linear_attn.out_proj",
"model.language_model.layers.19.self_attn.indexer.index_qk_proj",
"model.language_model.layers.19.self_attn.k_proj",
"model.language_model.layers.19.self_attn.o_proj",
"model.language_model.layers.19.self_attn.q_proj",
"model.language_model.layers.19.self_attn.v_proj",
"model.language_model.layers.2.linear_attn.in_proj_a",
"model.language_model.layers.2.linear_attn.in_proj_b",
"model.language_model.layers.2.linear_attn.in_proj_qkv",
"model.language_model.layers.2.linear_attn.in_proj_z",
"model.language_model.layers.2.linear_attn.out_proj",
"model.language_model.layers.20.linear_attn.in_proj_a",
"model.language_model.layers.20.linear_attn.in_proj_b",
"model.language_model.layers.20.linear_attn.in_proj_qkv",
"model.language_model.layers.20.linear_attn.in_proj_z",
"model.language_model.layers.20.linear_attn.out_proj",
"model.language_model.layers.21.linear_attn.in_proj_a",
"model.language_model.layers.21.linear_attn.in_proj_b",
"model.language_model.layers.21.linear_attn.in_proj_qkv",
"model.language_model.layers.21.linear_attn.in_proj_z",
"model.language_model.layers.21.linear_attn.out_proj",
"model.language_model.layers.22.linear_attn.in_proj_a",
"model.language_model.layers.22.linear_attn.in_proj_b",
"model.language_model.layers.22.linear_attn.in_proj_qkv",
"model.language_model.layers.22.linear_attn.in_proj_z",
"model.language_model.layers.22.linear_attn.out_proj",
"model.language_model.layers.23.self_attn.indexer.index_qk_proj",
"model.language_model.layers.23.self_attn.k_proj",
"model.language_model.layers.23.self_attn.o_proj",
"model.language_model.layers.23.self_attn.q_proj",
"model.language_model.layers.23.self_attn.v_proj",
"model.language_model.layers.24.linear_attn.in_proj_a",
"model.language_model.layers.24.linear_attn.in_proj_b",
"model.language_model.layers.24.linear_attn.in_proj_qkv",
"model.language_model.layers.24.linear_attn.in_proj_z",
"model.language_model.layers.24.linear_attn.out_proj",
"model.language_model.layers.25.linear_attn.in_proj_a",
"model.language_model.layers.25.linear_attn.in_proj_b",
"model.language_model.layers.25.linear_attn.in_proj_qkv",
"model.language_model.layers.25.linear_attn.in_proj_z",
"model.language_model.layers.25.linear_attn.out_proj",
"model.language_model.layers.26.linear_attn.in_proj_a",
"model.language_model.layers.26.linear_attn.in_proj_b",
"model.language_model.layers.26.linear_attn.in_proj_qkv",
"model.language_model.layers.26.linear_attn.in_proj_z",
"model.language_model.layers.26.linear_attn.out_proj",
"model.language_model.layers.27.self_attn.indexer.index_qk_proj",
"model.language_model.layers.27.self_attn.k_proj",
"model.language_model.layers.27.self_attn.o_proj",
"model.language_model.layers.27.self_attn.q_proj",
"model.language_model.layers.27.self_attn.v_proj",
"model.language_model.layers.28.linear_attn.in_proj_a",
"model.language_model.layers.28.linear_attn.in_proj_b",
"model.language_model.layers.28.linear_attn.in_proj_qkv",
"model.language_model.layers.28.linear_attn.in_proj_z",
"model.language_model.layers.28.linear_attn.out_proj",
"model.language_model.layers.29.linear_attn.in_proj_a",
"model.language_model.layers.29.linear_attn.in_proj_b",
"model.language_model.layers.29.linear_attn.in_proj_qkv",
"model.language_model.layers.29.linear_attn.in_proj_z",
"model.language_model.layers.29.linear_attn.out_proj",
"model.language_model.layers.3.self_attn.indexer.index_qk_proj",
"model.language_model.layers.3.self_attn.k_proj",
"model.language_model.layers.3.self_attn.o_proj",
"model.language_model.layers.3.self_attn.q_proj",
"model.language_model.layers.3.self_attn.v_proj",
"model.language_model.layers.30.linear_attn.in_proj_a",
"model.language_model.layers.30.linear_attn.in_proj_b",
"model.language_model.layers.30.linear_attn.in_proj_qkv",
"model.language_model.layers.30.linear_attn.in_proj_z",
"model.language_model.layers.30.linear_attn.out_proj",
"model.language_model.layers.31.self_attn.indexer.index_qk_proj",
"model.language_model.layers.31.self_attn.k_proj",
"model.language_model.layers.31.self_attn.o_proj",
"model.language_model.layers.31.self_attn.q_proj",
"model.language_model.layers.31.self_attn.v_proj",
"model.language_model.layers.32.linear_attn.in_proj_a",
"model.language_model.layers.32.linear_attn.in_proj_b",
"model.language_model.layers.32.linear_attn.in_proj_qkv",
"model.language_model.layers.32.linear_attn.in_proj_z",
"model.language_model.layers.32.linear_attn.out_proj",
"model.language_model.layers.33.linear_attn.in_proj_a",
"model.language_model.layers.33.linear_attn.in_proj_b",
"model.language_model.layers.33.linear_attn.in_proj_qkv",
"model.language_model.layers.33.linear_attn.in_proj_z",
"model.language_model.layers.33.linear_attn.out_proj",
"model.language_model.layers.34.linear_attn.in_proj_a",
"model.language_model.layers.34.linear_attn.in_proj_b",
"model.language_model.layers.34.linear_attn.in_proj_qkv",
"model.language_model.layers.34.linear_attn.in_proj_z",
"model.language_model.layers.34.linear_attn.out_proj",
"model.language_model.layers.35.self_attn.indexer.index_qk_proj",
"model.language_model.layers.35.self_attn.k_proj",
"model.language_model.layers.35.self_attn.o_proj",
"model.language_model.layers.35.self_attn.q_proj",
"model.language_model.layers.35.self_attn.v_proj",
"model.language_model.layers.36.linear_attn.in_proj_a",
"model.language_model.layers.36.linear_attn.in_proj_b",
"model.language_model.layers.36.linear_attn.in_proj_qkv",
"model.language_model.layers.36.linear_attn.in_proj_z",
"model.language_model.layers.36.linear_attn.out_proj",
"model.language_model.layers.37.linear_attn.in_proj_a",
"model.language_model.layers.37.linear_attn.in_proj_b",
"model.language_model.layers.37.linear_attn.in_proj_qkv",
"model.language_model.layers.37.linear_attn.in_proj_z",
"model.language_model.layers.37.linear_attn.out_proj",
"model.language_model.layers.38.linear_attn.in_proj_a",
"model.language_model.layers.38.linear_attn.in_proj_b",
"model.language_model.layers.38.linear_attn.in_proj_qkv",
"model.language_model.layers.38.linear_attn.in_proj_z",
"model.language_model.layers.38.linear_attn.out_proj",
"model.language_model.layers.39.self_attn.indexer.index_qk_proj",
"model.language_model.layers.39.self_attn.k_proj",
"model.language_model.layers.39.self_attn.o_proj",
"model.language_model.layers.39.self_attn.q_proj",
"model.language_model.layers.39.self_attn.v_proj",
"model.language_model.layers.4.linear_attn.in_proj_a",
"model.language_model.layers.4.linear_attn.in_proj_b",
"model.language_model.layers.4.linear_attn.in_proj_qkv",
"model.language_model.layers.4.linear_attn.in_proj_z",
"model.language_model.layers.4.linear_attn.out_proj",
"model.language_model.layers.40.linear_attn.in_proj_a",
"model.language_model.layers.40.linear_attn.in_proj_b",
"model.language_model.layers.40.linear_attn.in_proj_qkv",
"model.language_model.layers.40.linear_attn.in_proj_z",
"model.language_model.layers.40.linear_attn.out_proj",
"model.language_model.layers.41.linear_attn.in_proj_a",
"model.language_model.layers.41.linear_attn.in_proj_b",
"model.language_model.layers.41.linear_attn.in_proj_qkv",
"model.language_model.layers.41.linear_attn.in_proj_z",
"model.language_model.layers.41.linear_attn.out_proj",
"model.language_model.layers.42.linear_attn.in_proj_a",
"model.language_model.layers.42.linear_attn.in_proj_b",
"model.language_model.layers.42.linear_attn.in_proj_qkv",
"model.language_model.layers.42.linear_attn.in_proj_z",
"model.language_model.layers.42.linear_attn.out_proj",
"model.language_model.layers.43.self_attn.indexer.index_qk_proj",
"model.language_model.layers.43.self_attn.k_proj",
"model.language_model.layers.43.self_attn.o_proj",
"model.language_model.layers.43.self_attn.q_proj",
"model.language_model.layers.43.self_attn.v_proj",
"model.language_model.layers.44.linear_attn.in_proj_a",
"model.language_model.layers.44.linear_attn.in_proj_b",
"model.language_model.layers.44.linear_attn.in_proj_qkv",
"model.language_model.layers.44.linear_attn.in_proj_z",
"model.language_model.layers.44.linear_attn.out_proj",
"model.language_model.layers.45.linear_attn.in_proj_a",
"model.language_model.layers.45.linear_attn.in_proj_b",
"model.language_model.layers.45.linear_attn.in_proj_qkv",
"model.language_model.layers.45.linear_attn.in_proj_z",
"model.language_model.layers.45.linear_attn.out_proj",
"model.language_model.layers.46.linear_attn.in_proj_a",
"model.language_model.layers.46.linear_attn.in_proj_b",
"model.language_model.layers.46.linear_attn.in_proj_qkv",
"model.language_model.layers.46.linear_attn.in_proj_z",
"model.language_model.layers.46.linear_attn.out_proj",
"model.language_model.layers.47.self_attn.indexer.index_qk_proj",
"model.language_model.layers.47.self_attn.k_proj",
"model.language_model.layers.47.self_attn.o_proj",
"model.language_model.layers.47.self_attn.q_proj",
"model.language_model.layers.47.self_attn.v_proj",
"model.language_model.layers.5.linear_attn.in_proj_a",
"model.language_model.layers.5.linear_attn.in_proj_b",
"model.language_model.layers.5.linear_attn.in_proj_qkv",
"model.language_model.layers.5.linear_attn.in_proj_z",
"model.language_model.layers.5.linear_attn.out_proj",
"model.language_model.layers.6.linear_attn.in_proj_a",
"model.language_model.layers.6.linear_attn.in_proj_b",
"model.language_model.layers.6.linear_attn.in_proj_qkv",
"model.language_model.layers.6.linear_attn.in_proj_z",
"model.language_model.layers.6.linear_attn.out_proj",
"model.language_model.layers.7.self_attn.indexer.index_qk_proj",
"model.language_model.layers.7.self_attn.k_proj",
"model.language_model.layers.7.self_attn.o_proj",
"model.language_model.layers.7.self_attn.q_proj",
"model.language_model.layers.7.self_attn.v_proj",
"model.language_model.layers.8.linear_attn.in_proj_a",
"model.language_model.layers.8.linear_attn.in_proj_b",
"model.language_model.layers.8.linear_attn.in_proj_qkv",
"model.language_model.layers.8.linear_attn.in_proj_z",
"model.language_model.layers.8.linear_attn.out_proj",
"model.language_model.layers.9.linear_attn.in_proj_a",
"model.language_model.layers.9.linear_attn.in_proj_b",
"model.language_model.layers.9.linear_attn.in_proj_qkv",
"model.language_model.layers.9.linear_attn.in_proj_z",
"model.language_model.layers.9.linear_attn.out_proj",
"mtp.layers.0.mlp.experts"
],
"dropped_tensors": 3312,
"added_tensors": 5088
}