Jesse Gross 4d5ff25724 mlxrunner: Report actual memory usage from runner ...

The MLX runner previously reported a static VRAM estimate that was
computed at load time and consisted only of the weights. This is
strictly less than the actual memory usage, as it does not include
the KV cache or compute graph.

2026-02-25 15:06:37 -08:00

..

internal

docs: fix typos in repository documentation (#10683)

2025-11-15 20:22:29 -08:00

aliases.go

add ability to disable cloud (#14221)

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

auth_test.go

server: reject unexpected auth hosts (#13738)

2026-01-16 14:10:36 -05:00

auth.go

server: reject unexpected auth hosts (#13738)

2026-01-16 14:10:36 -05:00

create_test.go

Clean up the manifest and modelpath (#13807)

2026-01-21 11:46:17 -08:00

create.go

Clean up the manifest and modelpath (#13807)

2026-01-21 11:46:17 -08:00

download.go

Clean up the manifest and modelpath (#13807)

2026-01-21 11:46:17 -08:00

fixblobs_test.go

…

fixblobs.go

…

images_test.go

x/imagegen: add image edit capabilities (#13846)

2026-01-22 20:35:08 -08:00

images.go

x/imagegen: add image edit capabilities (#13846)

2026-01-22 20:35:08 -08:00

logprob.go

logprob: add bytes to logprobs (#13068)

2025-11-13 13:49:25 -08:00

model.go

Clean up the manifest and modelpath (#13807)

2026-01-21 11:46:17 -08:00

prompt_test.go

model: support for qwen3.5 architecture (#14378)

2026-02-24 20:08:05 -08:00

prompt.go

model: support for qwen3.5 architecture (#14378)

2026-02-24 20:08:05 -08:00

quantization_test.go

model: support for qwen3.5 architecture (#14378)

2026-02-24 20:08:05 -08:00

quantization.go

model: support for qwen3.5 architecture (#14378)

2026-02-24 20:08:05 -08:00

routes_aliases_test.go

add ability to disable cloud (#14221)

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

routes_aliases.go

cmd: ollama launch improvements (#14099)

2026-02-05 15:08:17 -08:00

routes_cloud_test.go

add ability to disable cloud (#14221)

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

routes_create_test.go

Clean up the manifest and modelpath (#13807)

2026-01-21 11:46:17 -08:00

routes_debug_test.go

server: use tiered VRAM-based default context length

2026-02-02 10:47:09 -08:00

routes_delete_test.go

Clean up the manifest and modelpath (#13807)

2026-01-21 11:46:17 -08:00

routes_generate_renderer_test.go

server: use tiered VRAM-based default context length

2026-02-02 10:47:09 -08:00

routes_generate_test.go

bugfix: better mlx model scheduling (#14290)

2026-02-17 13:57:05 -08:00

routes_harmony_streaming_test.go

preserve tool definition and call JSON ordering (#13525)

2026-01-05 18:03:36 -08:00

routes_list_test.go

Update the /api/create endpoint to use JSON (#7935)

2024-12-31 18:02:30 -08:00

routes_options_test.go

server: use tiered VRAM-based default context length

2026-02-02 10:47:09 -08:00

routes_test.go

server: return error when embedding contains NaN or Inf values (#13599)

2026-01-03 02:20:12 -05:00

routes.go

mlxrunner: Report actual memory usage from runner

2026-02-25 15:06:37 -08:00

sched_test.go

mlxrunner: Report actual memory usage from runner

2026-02-25 15:06:37 -08:00

sched.go

mlxrunner: Report actual memory usage from runner

2026-02-25 15:06:37 -08:00

sparse_common.go

Don't hard fail on sparse setup error

2024-08-09 12:16:19 -07:00

sparse_windows.go

Don't hard fail on sparse setup error

2024-08-09 12:16:19 -07:00

test_home_test.go

add ability to disable cloud (#14221)

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

upload.go

Clean up the manifest and modelpath (#13807)

2026-01-21 11:46:17 -08:00