CERBERUS/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-09-14 09:41:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
ollama/server
History
Daniel Hiltgen 16739dee60
server: align generate with native chat templates (#16878) 
* server: align generate with native chat templates

/api/generate rebuilt chat-like prompts through the Go template path even when the model selected its native GGUF Jinja chat template, so the same model rendered differently between generate and chat.

Route chat-like generate requests through the shared native chat preparation path, keep deprecated context and image handling working there, and keep explicit OLLAMA_GO_TEMPLATE overrides intact.

Fixes #16792

* review comments

Fall back to "{{ .Prompt }}" when lacking templates
2026-06-24 13:43:56 -07:00
..
internal
auth.go
auth_test.go
cloud_proxy.go
cloud_proxy_test.go
create.go server: classify mmproj GGUFs as projector layers (#16472) 2026-06-03 12:59:34 -07:00
create_test.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
download.go
fixblobs.go
fixblobs_test.go
gemma4_test.go models: add support for gemma4-12b (#16457) 2026-06-03 07:44:57 -07:00
images.go server: align generate with native chat templates (#16878) 2026-06-24 13:43:56 -07:00
images_test.go server: align generate with native chat templates (#16878) 2026-06-24 13:43:56 -07:00
inference_request_log.go
logprob.go
model.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
model_caches.go Reduce startup model hydration (#16215) 2026-05-19 15:53:08 -07:00
model_list_cache.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
model_list_cache_test.go Reduce startup model hydration (#16215) 2026-05-19 15:53:08 -07:00
model_recommendations.go launch: add plan-aware model gating (#16027) 2026-05-06 14:34:26 -07:00
model_recommendations_test.go launch: add plan-aware model gating (#16027) 2026-05-06 14:34:26 -07:00
model_resolver.go
model_resolver_test.go
model_show_cache.go Reduce startup model hydration (#16215) 2026-05-19 15:53:08 -07:00
model_show_cache_test.go Reduce startup model hydration (#16215) 2026-05-19 15:53:08 -07:00
prompt.go server: align generate with native chat templates (#16878) 2026-06-24 13:43:56 -07:00
prompt_test.go anthropic: Preserve Claude local image-path tool results in renderer-owned prompt formatting (#16047) 2026-05-12 00:02:17 -04:00
quantization.go convert: fixes for qwen3next model conversion (#16354) 2026-06-01 09:43:11 -07:00
quantization_stub_test.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
quantization_test.go convert: fixes for qwen3next model conversion (#16354) 2026-06-01 09:43:11 -07:00
renderer_resolution.go models: add support for gemma4-12b (#16457) 2026-06-03 07:44:57 -07:00
routes.go server: align generate with native chat templates (#16878) 2026-06-24 13:43:56 -07:00
routes_cloud_test.go
routes_create_test.go server: classify mmproj GGUFs as projector layers (#16472) 2026-06-03 12:59:34 -07:00
routes_debug_test.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
routes_delete_test.go
routes_generate_renderer_test.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
routes_generate_test.go server: align generate with native chat templates (#16878) 2026-06-24 13:43:56 -07:00
routes_harmony_streaming_test.go
routes_list_test.go openai: align models list with tags (#16556) 2026-06-05 17:59:05 -07:00
routes_options_test.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
routes_request_log_test.go
routes_test.go runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031) 2026-05-29 13:35:47 -07:00
routes_web_experimental_test.go
sched.go llm: context shift allow shiftable prompts (#16764) 2026-06-16 12:55:52 -07:00
sched_test.go llm: context shift allow shiftable prompts (#16764) 2026-06-16 12:55:52 -07:00
sparse_common.go
sparse_windows.go
test_home_test.go app: harden update flows (#16100) 2026-05-11 12:24:01 -07:00
upload.go