Daniel Hiltgen 96fb6d2fa9 nemotron_h: support the Nemotron 3.5 prompt layout (#17672) ... Select the 3.5 parser and renderer from its checkpoint template, preserve its prompt semantics, and map medium reasoning effort to the final-user annotation expected by the reference template. Exercise parser and renderer registration, create-time metadata inference, and exact Jinja parity so created models cannot silently fall back to the Nemotron 3 renderer.		2026-08-11 06:18:51 -07:00
..
client	nemotron_h: support the Nemotron 3.5 prompt layout (#17672)	2026-08-11 06:18:51 -07:00
blockfp8.go	model: add Laguna MLX support (#17237)	2026-07-24 18:24:53 -07:00
blockfp8_test.go	mlx: x/create rewrite (#16919)	2026-07-03 18:30:45 -07:00
classify.go	mlx: x/create rewrite (#16919)	2026-07-03 18:30:45 -07:00
classify_test.go	mlx: x/create rewrite (#16919)	2026-07-03 18:30:45 -07:00
cohere2moe.go	mlx: x/create rewrite (#16919)	2026-07-03 18:30:45 -07:00
create.go	mlx: implement Nemotron 3 Nano Omni (#17060)	2026-08-10 21:42:34 -07:00
create_test.go	mlx: implement Nemotron 3 Nano Omni (#17060)	2026-08-10 21:42:34 -07:00
draft.go	x/create: quantize a draft model's output head at the requested type	2026-07-24 17:26:58 -07:00
draft_test.go	x/create: quantize a draft model's output head at the requested type	2026-07-24 17:26:58 -07:00
dtype.go	mlx: Support NVIDIA TensorRT Model Optimizer import (#15566)	2026-04-27 18:28:10 -07:00
gemma4.go	create: keep vision towers at source precision when quantizing	2026-08-09 10:37:05 -07:00
gemma4_test.go	create: keep vision towers at source precision when quantizing	2026-08-09 10:37:05 -07:00
glimmer.go	Release v0.32.7 (#17646)	2026-08-10 04:04:56 -07:00
glimmer_test.go	Release v0.32.7 (#17646)	2026-08-10 04:04:56 -07:00
inventory.go	mlx: x/create rewrite (#16919)	2026-07-03 18:30:45 -07:00
inventory_test.go	mlx: x/create rewrite (#16919)	2026-07-03 18:30:45 -07:00
laguna.go	model: add Laguna MLX support (#17237)	2026-07-24 18:24:53 -07:00
laguna_test.go	model: add Laguna MLX support (#17237)	2026-07-24 18:24:53 -07:00
mlxthread.go	mlx: x/create rewrite (#16919)	2026-07-03 18:30:45 -07:00
nemotron_h.go	mlx: implement Nemotron 3 Nano Omni (#17060)	2026-08-10 21:42:34 -07:00
nemotron_h_test.go	mlx: implement Nemotron 3 Nano Omni (#17060)	2026-08-10 21:42:34 -07:00
pipeline.go	mlx: x/create rewrite (#16919)	2026-07-03 18:30:45 -07:00
pipeline_test.go	mlx: x/create rewrite (#16919)	2026-07-03 18:30:45 -07:00
plan.go	model: add Laguna MLX support (#17237)	2026-07-24 18:24:53 -07:00
plan_test.go	model: add Laguna MLX support (#17237)	2026-07-24 18:24:53 -07:00
prequant.go	mlx: x/create rewrite (#16919)	2026-07-03 18:30:45 -07:00
prequant_test.go	mlx: x/create rewrite (#16919)	2026-07-03 18:30:45 -07:00
quantize.go	mlx: x/create rewrite (#16919)	2026-07-03 18:30:45 -07:00
quantpolicy.go	create: keep vision towers at source precision when quantizing	2026-08-09 10:37:05 -07:00
qwen35.go	create: keep vision towers at source precision when quantizing	2026-08-09 10:37:05 -07:00
transform.go	mlx: x/create rewrite (#16919)	2026-07-03 18:30:45 -07:00
writer.go	mlx: x/create rewrite (#16919)	2026-07-03 18:30:45 -07:00
writer_test.go	mlx: x/create rewrite (#16919)	2026-07-03 18:30:45 -07:00