Skip to content

docs: mention apex-quant in the README#10412

Merged
mudler merged 1 commit into
masterfrom
docs/apex-quant-readme
Jun 20, 2026
Merged

docs: mention apex-quant in the README#10412
mudler merged 1 commit into
masterfrom
docs/apex-quant-readme

Conversation

@localai-bot

Copy link
Copy Markdown
Collaborator

Adds apex-quant to the Backends built by us section of the README.

It is placed as a short note right after the engines table (rather than inside it) because apex-quant is a per-tensor/per-layer quantization recipe for MoE models, not a native inference engine. The note highlights that it exploits MoE structural sparsity to produce GGUFs matching or beating Q8_0 quality, and runs out of the box on stock llama.cpp.

Assisted-by: Claude:claude-opus-4-8 [Claude Code]

Add apex-quant (MoE per-tensor/per-layer quantization recipe) to the
"Backends built by us" section as a note after the engines table, since
it is a quantization recipe rather than a native inference engine.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
@mudler mudler merged commit 1be959c into master Jun 20, 2026
56 of 57 checks passed
@mudler mudler deleted the docs/apex-quant-readme branch June 20, 2026 09:04
@localai-bot localai-bot added the kind/documentation Improvements or additions to documentation label Jun 23, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

kind/documentation Improvements or additions to documentation

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants