Skip to content

docs: align quantization and registry counts - #575

Merged
mudler merged 1 commit into
mudler:mainfrom
localai-org-maint-bot:codex/docs-alignment-20260813
Aug 13, 2026
Merged

docs: align quantization and registry counts#575
mudler merged 1 commit into
mudler:mainfrom
localai-org-maint-bot:codex/docs-alignment-20260813

Conversation

@localai-org-maint-bot

Copy link
Copy Markdown
Collaborator

Summary

  • replace the stale GGUF GPU-expansion claim with the current CPU and CUDA keep-quant boundary
  • document the implemented compressed-tensors MXFP4 W4A16 path and keep MXFP8 marked open
  • update the guarded registry count from 30 to 37

README news remains unchanged because this audit found no new supported architecture family or new binding benchmark headline after the latest README update.

Verification

  • python3 scripts/check-readme-structure.py
  • python3 tests/scripts/test_check_readme_structure.py
  • python3 scripts/check-public-doc-tables.py
  • python3 tests/scripts/test_check_public_doc_tables.py
  • python3 scripts/check-supported-models.py
  • python3 tests/scripts/test_check_supported_models.py
  • python3 scripts/check-agent-record.py
  • python3 tests/scripts/test_agent_record.py
  • python3 scripts/check-doc-checkpoint.py --staged
  • python3 tests/scripts/test_doc_checkpoint.py
  • python3 scripts/check-commit-trailers.py --range upstream/main..HEAD

BUILD still marked MXFP4 as planned and said all GPU GGUF weights expand. The implemented Marlin and keep-quant paths make both claims stale.

STATUS also retained the old 30-entry registry count after the guarded public list grew to 37.

FOLLOWING_AGENTS_PROTOCOL

Following-Agents-Protocol: true
AI-Assisted: true
Assisted-by: Codex:gpt-5 [Codex]
@mudler
mudler merged commit dd41622 into mudler:main Aug 13, 2026
23 of 25 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants