Experiment · runtime perf

CPU speedup bundle

The big win was fused accumulation inside the compiled trace; individual CPU tweaks need isolation before being credited. Retained outcome: worked with caveat.

Outcome
worked with caveat
Family
runtime perf
Evidence confidence
exact
Record
infrastructure

Evidence readout

all four items ON reached median `6.8 step/s` vs `5.0 step/s` baseline, `+36%`, with final loss `4.188-4.192` unchanged

What the attempt taught

The big win was fused accumulation inside the compiled trace; individual CPU tweaks need isolation before being credited.

Why it stopped or stayed bounded

The bundle produced a real host-side speedup, but QoS and compiled cosine LR were individually in the noise, prefetch stayed single-digit, and open CPU items remained.

Method and scope

  • Experiment family: runtime perf.
  • Record kind: infrastructure.

Disposition

Use the bundle as shipped, but keep Rust-FFI BPE, preallocated CPU buffers, and SVD-on-CPU AMX as separate future attempts.

This retained disposition is historical evidence, not authorization to restart the experiment. A new run needs a fresh question, frozen evaluator, explicit resource budget, and scoped tracking issue.

How to read this dossier

This canonical page separates the retained repository decision from the material that informed it. A source may describe an external claim, historical measurement, local observation, or planned procedure; those evidence classes are not interchangeable. Follow the provenance links before reusing a number or method.

Status and disposition describe what PostTrainLLM retained when this record was indexed. They are not a live product promise, a newly run benchmark, or permission to restart historical work. Unknown or unmeasured fields remain unknown rather than being treated as zero.

To reuse the record, first name the exact claim you need and trace it to the linked source. Then check whether the original environment, model revision, data split, evaluator, hardware, and budget match the proposed use. If they do not, treat the record as a hypothesis or design reference and run the smallest fresh comparison that can falsify it. Preserve negative outcomes and regressions beside any improvement; a local win on one slice does not silently become a general capability claim.

Source provenance

The normalized record comes from docs/attempts.json. The links below are the tracked evidence and explanatory sources preserved with the record.