docs: align GLM-5.3 public status - #2374
Open
localai-org-maint-bot wants to merge 1 commit into
Open
Conversation
The GLM-5.3 model landings moved the registry to 44 architectures, but the public overview still reported 43. The GLM feature rows also kept superseded refusal history after both forwards landed. Report the current CPU-only states and name the remaining gates. Record the CUDA keep-quant support without making a speed or parity claim. FOLLOWING_AGENTS_PROTOCOL Following-Agents-Protocol: true AI-Assisted: true Assisted-by: Codex:gpt-5.6-sol [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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What changed
Why
Recent GLM-5.3 model and quantization landings made the public overview stale. The README still described the GLM-5.3-Flash forward as incomplete, and
docs/FEATURES.mdstill said GLM-5.3 loaded and forwarded nothing.Verification
python3 scripts/check-readme-structure.pypython3 tests/scripts/test_check_readme_structure.pypython3 scripts/check-supported-models.pypython3 tests/scripts/test_check_supported_models.pypython3 scripts/check-agent-record.pypython3 scripts/check-model-checklist.pypython3 scripts/check-env-doc.pypython3 scripts/check-commit-trailers.py --range upstream/main..HEADgit diff --checkscripts/agent-preflight.shpasses all documentation and record gates. Two host-dependent checks remain unavailable: release-workflow validation needs PyYAML, and test-registration configuration aborts in the host toolchain. This documentation-only change does not modify either surface.Claims
No new speed or oracle-parity claim is made. GLM-5.3-Flash is described as coherent CPU output, and GLM-5.3 as a synthetic first-token forward only.
FOLLOWING_AGENTS_PROTOCOL
Following-Agents-Protocol: true
AI-Assisted: true
Assisted-by: Codex:gpt-5.6-sol [Codex]