Shayan khan 864db8e3d3 fix(backends): honor enable_thinking=false in mlx and vllm-omni (#11962) ...

The mlx, mlx-vlm, mlx-distributed and vllm-omni backends only forwarded
enable_thinking when the metadata value was "true". A "false" value never
reached apply_chat_template, so requests with thinking disabled (for
example a realtime pipeline with disable_thinking: true) still used the
chat template default. Apply the same coerce that #11715 added to sglang
and vllm.

Assisted-by: Claude:claude-opus-5

Signed-off-by: devv-shayan <shayankhanx1x@gmail.com>

2026-09-11 18:01:51 +02:00

..

backend.py

fix(backends): honor enable_thinking=false in mlx and vllm-omni (#11962)

2026-09-11 18:01:51 +02:00

coordinator.py

feat(mlx-distributed): add new MLX-distributed backend (#8801)

2026-03-09 17:29:32 +01:00

install.sh

feat(mlx-distributed): add new MLX-distributed backend (#8801)

2026-03-09 17:29:32 +01:00

Makefile

feat(mlx-distributed): add new MLX-distributed backend (#8801)

2026-03-09 17:29:32 +01:00

mlx_cache.py

feat(mlx-distributed): add new MLX-distributed backend (#8801)

2026-03-09 17:29:32 +01:00

requirements-cpu.txt

feat(mlx-distributed): add new MLX-distributed backend (#8801)

2026-03-09 17:29:32 +01:00

requirements-cublas12.txt

feat(mlx-distributed): add new MLX-distributed backend (#8801)

2026-03-09 17:29:32 +01:00

requirements-cublas13.txt

feat(mlx-distributed): add new MLX-distributed backend (#8801)

2026-03-09 17:29:32 +01:00

requirements-l4t12.txt

feat(mlx-distributed): add new MLX-distributed backend (#8801)

2026-03-09 17:29:32 +01:00

requirements-l4t13.txt

feat(mlx-distributed): add new MLX-distributed backend (#8801)

2026-03-09 17:29:32 +01:00

requirements-mps.txt

feat(mlx-distributed): add new MLX-distributed backend (#8801)

2026-03-09 17:29:32 +01:00

requirements.txt

feat(mlx-distributed): add new MLX-distributed backend (#8801)

2026-03-09 17:29:32 +01:00

run.sh

feat(mlx-distributed): add new MLX-distributed backend (#8801)

2026-03-09 17:29:32 +01:00

sharding.py

feat(mlx-distributed): add new MLX-distributed backend (#8801)

2026-03-09 17:29:32 +01:00

test.py

fix(backends): honor enable_thinking=false in mlx and vllm-omni (#11962)

2026-09-11 18:01:51 +02:00

test.sh

feat(mlx-distributed): add new MLX-distributed backend (#8801)

2026-03-09 17:29:32 +01:00