Devon Rifkin 2c2f4deaa9 openai: refactor to split compat layer and middleware ...

This makes the core openai compat layer independent of the middleware
that adapts it to our particular gin routes

2025-10-05 14:18:56 -07:00

..

internal

refactor: use the built-in max/min to simplify the code (#12280)

2025-09-16 17:14:21 -07:00

auth.go

…

create_test.go

engine: add remote proxy (#12307)

2025-09-17 14:40:53 -07:00

create.go

engine: add remote proxy (#12307)

2025-09-17 14:40:53 -07:00

download.go

…

fixblobs_test.go

…

fixblobs.go

…

images_test.go

…

images.go

templates: fix crash in improperly defined templates (#12483)

2025-10-02 17:25:55 -07:00

layer.go

…

manifest_test.go

…

manifest.go

…

model.go

…

modelpath_test.go

…

modelpath.go

…

prompt_test.go

…

prompt.go

add qwen3-coder tool support

2025-09-15 11:33:47 -07:00

quantization_test.go

…

quantization.go

…

routes_create_test.go

engine: add remote proxy (#12307)

2025-09-17 14:40:53 -07:00

routes_debug_test.go

Use runners for GPU discovery (#12090)

2025-10-01 15:12:32 -07:00

routes_delete_test.go

…

routes_generate_test.go

Use runners for GPU discovery (#12090)

2025-10-01 15:12:32 -07:00

routes_harmony_streaming_test.go

Use runners for GPU discovery (#12090)

2025-10-01 15:12:32 -07:00

routes_list_test.go

…

routes_test.go

engine: add remote proxy (#12307)

2025-09-17 14:40:53 -07:00

routes.go

openai: refactor to split compat layer and middleware

2025-10-05 14:18:56 -07:00

sched_test.go

Use runners for GPU discovery (#12090)

2025-10-01 15:12:32 -07:00

sched.go

Use runners for GPU discovery (#12090)

2025-10-01 15:12:32 -07:00

sparse_common.go

…

sparse_windows.go

…

upload.go

…