Patrick Devine d126467d5d x/mlxrunner: replace sampler interface chain with single stateful Sampler (#14652) ...

- Collapse MLX sampling state into a single sample.Sampler struct (options + history).
- Replace interface-based sampler chain (TopP, TopK, penalty, etc.) with function-based transforms.
- Update request/pipeline wiring to use *sample.Sampler, seed history from prompt tokens, and append generated tokens each step.
- Implement top_p, min_p, repeat_penalty, and frequency_penalty

2026-03-07 17:50:57 -08:00

..

agent

x/cmd: enable web search and web fetch with flag (#13690)

2026-01-12 13:59:40 -08:00

cmd

Reapply "don't require pulling stubs for cloud models" again (#14608)

2026-03-06 14:27:47 -08:00

create

mlx: int4 groupsize 64 (#14682)

2026-03-06 16:39:47 -08:00

imagegen

chore: remove old imagegen LLMs models (#14597)

2026-03-03 13:23:40 -08:00

mlxrunner

x/mlxrunner: replace sampler interface chain with single stateful Sampler (#14652)

2026-03-07 17:50:57 -08:00

models

parsers: repair unclosed arg_value tags in GLM tool calls (#14656)

2026-03-06 14:08:34 -08:00

server

bugfix: display the parameter count correctly in mlx for ollama show (#14285)

2026-02-16 13:03:34 -08:00

tokenizer

consolidate the tokenizer (#14327)

2026-02-19 15:55:45 -08:00

tools

add ability to disable cloud (#14221)

2026-02-12 15:47:00 -08:00