Daniel HiltgenandGitHub f52b9e742d Update gemma renderers (#19241) ...

* renderers: add gemma4-nemotron renderer

Add a Gemma 4 renderer variant that renders assistant content before
its tool calls rather than after the tool responses. Models opt in with
RENDERER gemma4-nemotron; gemma4 auto-detection is unchanged.

Adds the corresponding chat template as a test fixture for Jinja parity
checks.

* mlx: support Gemma 4 targets with DFlash drafts

Load a draft-owned output head when its config requires one, while preserving the target-head path used by existing DFlash models.

Expose Gemma 4 hidden-state taps and raw logits for speculative decoding. Report safetensors target precision independently of quantized draft weights.

2026-10-23 07:12:11 -07:00

..

parsers

mlx: add Flint model support (#19181)

2026-10-21 07:45:50 -07:00

renderers

Update gemma renderers (#19241)

2026-10-23 07:12:11 -07:00