Jesse Gross 24e038d56a mlxrunner: add logprobs support ...

Match the ollamarunner and OpenAI semantics: raw, full-vocab log-softmax
with the top-K ranked by probability. Skipped on the GPU when the request
doesn't ask for logprobs so decode doesn't pay for it otherwise.

2026-04-20 17:43:00 -07:00

..

gemma3

mlx: quantized embeddings, fast SwiGLU, and runtime fixes (#14884)

2026-03-17 11:21:38 -07:00

gemma4

mlxrunner: add logprobs support

2026-04-20 17:43:00 -07:00

glm4_moe_lite

mlx: fuse sigmoid router head in glm4_moe_lite

2026-04-20 15:02:14 -07:00

llama

models: fuse MLP activation functions via mlx_compile

2026-04-14 16:38:32 -07:00

nn

mlxrunner: add logprobs support

2026-04-20 17:43:00 -07:00

qwen3

models: fuse MLP activation functions via mlx_compile

2026-04-14 16:38:32 -07:00

qwen3_5

models: fuse MLP activation functions via mlx_compile

2026-04-14 16:38:32 -07:00

qwen3_5_moe

MLX: add header vendoring and remove go build tag (#14642)

2026-03-09 17:24:45 -07:00