rob thijssen
7c19da9361
All checks were successful
CI / Format (push) Successful in 40s
build-prerelease / Resolve version stamps (push) Successful in 45s
CI / Clippy (push) Successful in 2m27s
build-prerelease / Build cortex binary (push) Successful in 4m24s
build-prerelease / Build neuron-blackwell (push) Successful in 4m0s
build-prerelease / Package cortex RPM (push) Successful in 1m18s
build-prerelease / Build neuron-ampere (push) Successful in 5m10s
build-prerelease / Build neuron-ada (push) Successful in 4m56s
build-prerelease / Package helexa-neuron-ada RPM (push) Successful in 3m1s
build-prerelease / Package helexa-neuron-ampere RPM (push) Successful in 2m57s
build-prerelease / Package helexa-neuron-blackwell RPM (push) Successful in 3m47s
build-prerelease / Publish to rpm.lair.cafe (unstable) (push) Successful in 1m1s
CI / Test (push) Successful in 4m24s
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
Three additive diagnostics that turn the 2026-05-27 q5k Qwen3.6-27B incident from "guess at KV cache / quant sizes" into "read the journal": 1. Construction-complete summary in TpQwen3_5ForCausalLM::load and TpQwen3ForCausalLM::load. After the last "after layer N" log fires, each rank emits a single info line with: free_mb/total_mb (the number that drops by ~9 GB between per-layer and first-request on beast, with no inference traffic), every resolved config knob (vocab_size, hidden_size, num_layers, head_dim, num_kv_heads, max_position_embeddings), and a per-token KV-cache byte estimate. For Qwen3-Next also includes the linear/full-attention layer split so the hybrid architecture's cache cost is unambiguous. 2. Logits health snapshot on sample failure. Today the failure logs "A weight is negative, too large or not a valid number" with no context — was it a NaN cascade, an Inf, a negative weight? `logits_health(&logits)` computes nan/pos_inf/neg_inf/neg counts plus finite_min/max/mean on the failure path (zero cost on the success path) and emits a warn line just before the wrapper's terminal "failed, model marked poisoned" log. Wired into both the prefill and decode sample sites of the non-streaming AND streaming TP chat paths. 3. VRAM snapshot at prefill complete + every decode step. The "prefill complete" info line now carries vram_free_mb so the activations + KV growth from the prefill itself is visible. The per-step trace line gets vram_free_mb too, so an operator running with RUST_LOG=trace can watch headroom shrink token by token. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>