rob thijssen
e71181499e
All checks were successful
build-prerelease / Resolve version stamps (push) Successful in 42s
build-prerelease / Build neuron-blackwell (push) Successful in 3m43s
build-prerelease / Build cortex binary (push) Successful in 4m25s
build-prerelease / Package cortex RPM (push) Successful in 1m26s
build-prerelease / Build neuron-ampere (push) Successful in 5m23s
build-prerelease / Build neuron-ada (push) Successful in 4m56s
build-prerelease / Package helexa-neuron-ampere RPM (push) Successful in 2m52s
build-prerelease / Package helexa-neuron-ada RPM (push) Successful in 2m59s
build-prerelease / Package helexa-neuron-blackwell RPM (push) Successful in 3m42s
build-prerelease / Publish to rpm.lair.cafe (unstable) (push) Successful in 1m1s
CI / Format (push) Successful in 30s
CI / Clippy (push) Successful in 2m19s
CI / Test (push) Successful in 4m21s
CI / Build cortex SRPM (push) Has been skipped
CI / Build neuron SRPM (push) Has been skipped
CI / Publish cortex to COPR (push) Has been skipped
CI / Publish neuron to COPR (push) Has been skipped
CI / Bump version in source (push) Has been skipped
TpQwen3_5ForCausalLM::lm_head is now a MaybeQuantLinear. When the load spec has quant set and tie_word_embeddings is false, lm_head's (vocab_size, hidden_size) weight is quantized in-situ at load time along with all the per-layer linears. The non-tied case on Qwen3.6-27B saves ~1.7 GB per rank vs bf16 (248320 x 5120 x 2 bytes = 2.42 GB -> ~700 MB at Q5K) and shaves a small amount of decode latency from the per-token logits matmul. Tied case (tie_word_embeddings=true) keeps the lm_head plain even when quant is set — quantizing the shared tensor would corrupt the embedding lookup, and the tied case already gets the memory win from only holding one copy. This is the last MaybeQuantLinear hookup in the Qwen3-Next TP path. The dense Qwen3 path (tp_qwen3.rs) is unchanged — defer until it's the bottleneck for a model that actually needs TP at consumer scale. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>