rob thijssen
5c4c8e0eba
All checks were successful
build-prerelease / Resolve version stamps (push) Successful in 33s
CI / Format (push) Successful in 35s
CI / Clippy (push) Successful in 2m12s
build-prerelease / Build neuron-blackwell (push) Successful in 3m49s
CI / Test (push) Successful in 4m27s
CI / Build cortex SRPM (push) Has been skipped
CI / Publish cortex to COPR (push) Has been skipped
CI / Build neuron SRPM (push) Has been skipped
CI / Publish neuron to COPR (push) Has been skipped
CI / Bump version in source (push) Has been skipped
build-prerelease / Build neuron-ampere (push) Successful in 4m50s
build-prerelease / Build neuron-ada (push) Successful in 5m12s
build-prerelease / Build cortex binary (push) Successful in 4m14s
build-prerelease / Package cortex RPM (push) Successful in 1m17s
build-prerelease / Package helexa-neuron-ampere RPM (push) Successful in 2m50s
build-prerelease / Package helexa-neuron-ada RPM (push) Successful in 2m52s
build-prerelease / Package helexa-neuron-blackwell RPM (push) Successful in 3m43s
build-prerelease / Publish to rpm.lair.cafe (unstable) (push) Successful in 59s
Qwen3-Next is a multimodal architecture whose text core sits under
`model.language_model.*` — sibling to `model.visual.*` (vision tower)
and to top-level `lm_head` / `mtp.*`. Every text-side tensor in the
safetensors files carries that prefix:
model.language_model.embed_tokens.weight
model.language_model.layers.{i}.{input,post_attention}_layernorm.weight
model.language_model.layers.{i}.linear_attn.{in_proj_*, conv1d.weight, A_log, dt_bias, norm.weight, out_proj.weight}
model.language_model.layers.{i}.self_attn.{q,k,v,o}_proj.weight + {q,k}_norm.weight
model.language_model.layers.{i}.mlp.{gate,up,down}_proj.weight
model.language_model.norm.weight
lm_head.weight (top-level; not under language_model)
The single-pre-emptive fix is in Qwen3_5Model::load — derive a
`text_vb = vb.pp("model.language_model")` once and walk
embed_tokens / layers / norm from there. `lm_head` stays at the
top-level VB; that path was already correct.
The non-text tensors (`model.visual.*`, `mtp.*`) are ignored: we
don't reference them, so the safetensors mmap is fine even though
the bytes are loaded into the address space.
After this, the load that was failing at
"cannot find tensor model.embed_tokens.weight" should proceed to
materialising the actual layer weights — where any further bugs
will be substantive architecture issues rather than naming ones.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>