transformers

a562fb8c - finegrained: consume modelopt's calibrated globals, and fuse a model's per-expert output norm

finegrained: consume modelopt's calibrated globals, and fuse a model's per-expert output norm modelopt NVFP4 checkpoints ship a second-level global per projection and a calibrated `input_scale`; both now reach the kernels, in either of the two layouts such a checkpoint uses — one tensor per expert per projection (GLM-5.2) or one stacked tensor per layer (the fused vLLM layout). A gate|up stack arrives with two weight globals per expert, calibrated separately. One conversion op owns every global of a layer and merges them to the one-per-expert the kernels take: the stack keeps the gate's, and the up half's folds onto the down projection, whose weight global scales the expert output back up and whose calibrated input global moves the other way, keeping the requantized intermediate on the range the checkpoint calibrated. That is exact arithmetic on fp32 scalars, unlike rescaling the up half's e4m3 block scales. Many-to-many converters are now opt-in per op (`ConversionOps.supports_many_to_many`) rather than a private whitelist. A model states its per-expert output norm the way it states its activation: `use_experts_implementation(post_expert_norm="<name>")` plus an `_apply_post_norm` the class must define. A name the kernels implement rides as that name and is folded into their reduce; anything else is the module, called on the routed rows. The DeepGEMM experts paths, which have no slot for such a norm, refuse instead of dropping it. Weight-only modules hold no activation global, since nothing there quantizes activations: the parameters are not allocated, the converters for them are not emitted, and a calibrated checkpoint's `input_scale` keys are ignored for that run. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>