Files
nvfp4-megamoe-kernel/vllm
biondizzle e6ed9facf3 fix: indexer + shared_experts + compressor checkpoint→model key renames
Three categories of missed renames in CKPT_KEY_SUBST:

1. Shared experts: .shared_experts.gate_proj.→.ffn.shared_experts.w1. fired
   but break prevented .mlp.→.ffn. from also applying, producing
   mlp.ffn.shared_experts.w1. (double prefix). Fixed by including .mlp.
   in the pattern. Added missing .shared_experts.down_proj. rule.

2. Indexer (layers 2+): .self_attn.compressor.indexer.* was caught by the
   generic .self_attn.compressor.→.attn.mla_attn.compressor. rule, producing
   wrong path attn.mla_attn.compressor.indexer.* instead of attn.indexer.*.
   Added indexer-specific patterns (q_b_proj→wq_b, kv_norm→k_norm,
   position_bias→compressor.ape, gate_proj→compressor.wgate,
   kv_proj→compressor.wkv) before the generic compressor rule.

3. Compressor kv_proj/gate_proj: old .compressor.kv_proj.→.compressor.wkv.
   pattern could never fire because .self_attn.compressor. matched first
   (break). Merged into combined patterns that handle both the
   self_attn.compressor→attn.mla_attn.compressor path AND the projection
   rename in one step.
2026-05-15 00:39:37 +00:00
..