Artifact contract
A numerical and performance comparison that keeps reference math, optimized kernel, dispatch geometry, and end-to-end effect separate.
This systems benchmark is classified as guided replay. Workload guidance: read-only replay; fresh kernel loops require approval.
Build
Trace reference attention and matmul before inspecting their optimized counterparts.
Modify
Change precision, tile size, workgroup shape, or architecture one dimension at a time.
Tune
Tune the measured bottleneck rather than optimizing a convenient microbenchmark.
Prove
Require numerical parity, warmed timing, memory evidence, and end-to-end impact.
Package
Retain source revision, device, shapes, precision, raw timings, and parity tolerance.
CLI surface
- Run: posttrainllm bench
- Run: posttrainllm bench-train
- Run: posttrainllm experimental train-heads
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/learn/artifact-journey.json. The links below are the tracked evidence and explanatory sources preserved with the record.
- python_ref/model.py ↗
- webgpu/attention_fa2.wgsl ↗
- docs/performance/fa2_backward_notes.md ↗
- Trace reference attention and matmul before inspecting their optimized counterparts. ↗
- Change precision, tile size, workgroup shape, or architecture one dimension at a time. ↗
- Tune the measured bottleneck rather than optimizing a convenient microbenchmark. ↗
- Require numerical parity, warmed timing, memory evidence, and end-to-end impact. ↗
- Retain source revision, device, shapes, precision, raw timings, and parity tolerance. ↗