docs(readme): SHIP-007 GPU known-issue warning per FALSIFY-MODEL-1-SHIP-CPU-004#1114
Merged
Conversation
…-SHIP-CPU-004 Adds a "Known Issue (SHIP-007)" callout to README Quick Start that recommends `--no-gpu` for the canonical 7B Q4K teacher (paiml/qwen2.5-coder-7b-apache-q4k-v1). Per SPEC-SHIP-TWO-001 §40 (PR #1111) + apr-cli-model-1-ship-via-cpu-v1.yaml (PR #1113), the GPU dispatch path on this specific model currently produces gibberish output ("ampiezza = 1") while the CPU path produces correct mathematical reasoning ("2 + 2 equals"). This satisfies FALSIFY-MODEL-1-SHIP-CPU-004 (user-facing docs warn about GPU known-issue): $ grep -rE -- '(--no-gpu|SHIP-007|GPU known issue|use --no-gpu)' \ README.md docs/ apr-cookbook/ README.md:> **Known Issue (SHIP-007)**: For the canonical 7B Q4K teacher README.md:> (paiml/qwen2.5-coder-7b-apache-q4k-v1), use `--no-gpu` until the README.md:> apr run paiml/qwen2.5-coder-7b-apache-q4k-v1 "What is 2+2?" --no-gpu Five-whys (consistent with §40): 1. Why does the README need this warning? Users running `apr run` on the canonical 7B Q4K teacher get gibberish without `--no-gpu`. 2. Why? The default GPU dispatch path has SHIP-007 (GPU FP8/dequant defect). 3. Why now? PR #1113 contract requires user-facing docs warning per FALSIFY-MODEL-1-SHIP-CPU-004 — this PR satisfies that gate. 4. Why this README placement? Quick Start is the highest-traffic section; users see it first. 5. What removes the warning? GPU fix lands → contract bumps to v2.0.0 → README warning becomes obsolete and gets removed in same PR. Spec ref: §40.6 Option A (PR #1111). Contract ref: apr-cli-model-1-ship-via-cpu-v1 (PR #1113). Coverage: contributes to MODEL-1 SHIP gate completeness. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds a "Known Issue (SHIP-007)" callout to the README Quick Start that recommends `--no-gpu` for the canonical 7B Q4K teacher.
Why this matters
Per FALSIFY-MODEL-1-SHIP-CPU-004 (apr-cli-model-1-ship-via-cpu-v1.yaml v1.0.0, PR #1113), the SHIP gate REQUIRES user-facing docs to warn about the GPU known-issue. This PR satisfies that gate.
Without the warning, users running:
```bash
apr run paiml/qwen2.5-coder-7b-apache-q4k-v1 "What is 2+2?"
```
get gibberish ("ampiezza = 1") because the default GPU path triggers SHIP-007.
With the warning, users follow the recommended:
```bash
apr run paiml/qwen2.5-coder-7b-apache-q4k-v1 "What is 2+2?" --no-gpu
```
and get correct output ("2 + 2 equals").
Verification
```
$ grep -rE -- '(--no-gpu|SHIP-007|GPU known issue|use --no-gpu)' README.md docs/
README.md:> Known Issue (SHIP-007): For the canonical 7B Q4K teacher
README.md:> (paiml/qwen2.5-coder-7b-apache-q4k-v1), use `--no-gpu` until the
README.md:> apr run paiml/qwen2.5-coder-7b-apache-q4k-v1 "What is 2+2?" --no-gpu
```
✓ FALSIFY-MODEL-1-SHIP-CPU-004 PASSES.
Plain progress on shipping models
This is the LAST gate-completing piece for the MODEL-1 SHIP-via-CPU chain. With this + #1113 + #1111 (§40 spec) all merged:
MODEL-1 ships TODAY via CPU once these 4 PRs merge to main.
Methodology adherence
Test plan
🤖 Generated with Claude Code