docs: clarify Qwen3.8 benchmark limits - #3104
Open
localai-org-maint-bot wants to merge 3 commits into
Open
Conversation
The public pages omit a recent comparison and disagree about an FP8 gate. Record the editorial scope before correcting those claims. FOLLOWING_AGENTS_PROTOCOL Following-Agents-Protocol: true AI-Assisted: true Assisted-by: Codex:GPT-6 [Codex]
The benchmark index omits incomplete comparator repetitions. The model guide also denies a token gate that its preceding section records. Align both summaries with the evidence and add the September comparison to README News without a speed or correctness claim. Issue: ISSUE-LOCAL-01M221WAVSK2STJ49Y3WTDSDS3 FOLLOWING_AGENTS_PROTOCOL Following-Agents-Protocol: true AI-Assisted: true Assisted-by: Codex:GPT-6 [exec]
Keep the source anchors and validation limits with the pending PR. The issue remains open until upstream integration. FOLLOWING_AGENTS_PROTOCOL Following-Agents-Protocol: true AI-Assisted: true Assisted-by: Codex:GPT-6 [Codex]
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The Qwen3.8 model guide denies a token comparison that its earlier section records. Clarify that the CUDA shape tests and the later model token gate are separate measurements.
Add the September EXL3 comparison to README News. State that comparator repetitions are incomplete, configurations differ, and the run has no correctness gate. Expose the incomplete repetitions in the benchmark index.
The changes use the current source and committed evidence. No runtime behavior or measured number changes. The scope and evidence anchors are in
.agents/specs/qwen38-public-doc-refresh.md, which owns ISSUE-LOCAL-01M221WAVSK2STJ49Y3WTDSDS3.CPU-only validation passed:
python3 scripts/check-readme-structure.pypython3 scripts/check-benchmark-index.pypython3 scripts/check-site.pypython3 scripts/check-agent-record.pygit diff --check.Full preflight was attempted but is not green. The temporary Alpine tool environment caused release-packaging subprocess failures and initially lacked validation dependencies. Focused documentation checks pass after local tool setup. No GPU tests or new benchmarks were run.
FOLLOWING_AGENTS_PROTOCOL
Following-Agents-Protocol: true
AI-Assisted: true
Assisted-by: Codex:GPT-6 [Codex]