Patrick Devine 857cffd22a bugfix: fix crash bug in token cache logic ...

This change fixes a problem in the token cache logic to avoid panics caused by empty token arrays
by ensuring at least one token remains on full cache hits in the relevant function. The happens
if there is an exact match in the cache on subsequent generations.

2026-02-26 18:35:44 -08:00

..

agent

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

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

cmd

add ability to disable cloud (#14221)

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

create

model: add qwen3 support to mlxrunner (#14293)

2026-02-17 13:58:49 -08:00

imagegen

update mlx-c bindings to 0.5.0 (#14380)

2026-02-23 16:44:29 -08:00

mlxrunner

bugfix: fix crash bug in token cache logic

2026-02-26 18:35:44 -08:00

models

mlxrunner: Fix memory leaks with pin/sweep lifecycle management

2026-02-23 09:50:07 -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