Devon Rifkin 2e9d9acf18 add ability to turn on debug request logging ...

If `OLLAMA_DEBUG_LOG_REQUESTS` is set, then on server startup a temp
folder will be created. Upon any inference request, the body will be
logged to a file in this folder, as well as a small shell script to
"replay" the request using cURL.

This is just intended for debugging scenarios, not as something to turn
on normally.

2026-02-05 15:14:35 -08:00

..

internal

docs: fix typos in repository documentation (#10683)

2025-11-15 20:22:29 -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

server: replace blob prefix separator from ':' to '-' (#3146)

2024-03-14 20:18:06 -07:00

fixblobs.go

server: replace blob prefix separator from ':' to '-' (#3146)

2024-03-14 20:18:06 -07:00

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

inference_request_log.go

add ability to turn on debug request logging

2026-02-05 15:14:35 -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

server: optimize chatPrompt to reduce tokenization calls (#14040)

2026-02-04 01:21:31 -08:00

prompt.go

server: optimize chatPrompt to reduce tokenization calls (#14040)

2026-02-04 01:21:31 -08:00

quantization_test.go

Reapply "feat: incremental gguf parser (#10822)" (#11114) (#11119)

2025-06-20 11:11:40 -07:00

quantization.go

model: add qwen3-next architecture (#14051)

2026-02-03 23:27:21 -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

server: use tiered VRAM-based default context length

2026-02-02 10:47:09 -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_request_log_test.go

add ability to turn on debug request logging

2026-02-05 15:14:35 -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

add ability to turn on debug request logging

2026-02-05 15:14:35 -08:00

sched_test.go

server: fix ollama ps showing configured instead of actual context length

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

sched.go

scheduler: default parallel=1 for qwen3next/lfm (#14103)

2026-02-05 12:48:25 -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

upload.go

Clean up the manifest and modelpath (#13807)

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