mirror/ollama

0 Fork 0

mirror of https://github.com/ollama/ollama.git synced 2026-09-14 07:00:55 -04:00

Files

T

History

Daniel Hiltgen 855f4bf989 Report cached prompt tokens (#17943 )

* Report cached prompt tokens

Add prompt_eval_cached_count to native responses and expose equivalent cached-token fields through the OpenAI- and Anthropic-compatible APIs. Keep prompt_eval_count as the logical input total while excluding cache hits from CLI and benchmark prefill rates. Surface processed and cached prompt counts in benchmark output.

Collect cache counts from llama-server and MLX, preserve coherent metrics across two-pass structured generation.

Fixes #8008

Related to #15758

* review comments

2026-09-02 09:30:44 -07:00

..

Report cached prompt tokens (#17943 )

2026-09-02 09:30:44 -07:00

fix(docs): correct typos found during code review (#17579 )

2026-08-31 08:59:55 -07:00

launch: add DeepSeek Harness integration (#17733 )

2026-08-13 15:19:02 -07:00

docs: claude docs (#18006 )

2026-08-25 19:34:13 -07:00

tools/extract-examples

docs: add docs for v1/responses and rework openai compat section (#13416 )

2025-12-11 17:39:40 -08:00

api.md

Report cached prompt tokens (#17943 )

2026-09-02 09:30:44 -07:00

cli.mdx

docs: update docs examples to use Gemma 4 instead of Gemma 3 (#16607 )

2026-06-07 12:43:13 -07:00

cloud.mdx

docs: fix broken links (#17676 )

2026-08-11 14:36:39 -07:00

context-length.mdx

docs: update docs examples to use Gemma 4 instead of Gemma 3 (#16607 )

2026-06-07 12:43:13 -07:00

development.md

llama: enable FA on CUDA CC 6.x GPUs (#16994 )

2026-07-02 17:11:39 -07:00

docker.mdx

runner: Remove CGO engines, use llama-server exclusively for GGML models (#16031 )

2026-05-29 13:35:47 -07:00

docs.json

docs: document Claude Desktop integration (#18004 )

2026-08-25 19:12:21 -07:00

examples.md

docs: fix broken links (#17676 )

2026-08-11 14:36:39 -07:00

faq.mdx

docs: fix broken links (#17676 )

2026-08-11 14:36:39 -07:00

favicon-dark.svg

docs: add docs for docs.ollama.com (#12805 )

2025-10-28 13:18:48 -07:00

favicon.svg

docs: add docs for docs.ollama.com (#12805 )

2025-10-28 13:18:48 -07:00

gpu.mdx

docs: fix broken links (#17676 )

2026-08-11 14:36:39 -07:00

import.mdx

docs: fix broken links (#17676 )

2026-08-11 14:36:39 -07:00

index.mdx

docs: redesign docs landing and integrations overview (#16807 )

2026-06-24 16:28:28 -04:00

linux.mdx

docs: fix broken links (#17676 )

2026-08-11 14:36:39 -07:00

logo.svg

docs: add docs for docs.ollama.com (#12805 )

2025-10-28 13:18:48 -07:00

macos.mdx

docs: update readme and links (#12809 )

2025-10-28 16:20:02 -07:00

modelfile.mdx

api: stop applying repeat_penalty 1.1 to models that don't set one

2026-08-11 21:47:51 -07:00

ollama-logo.svg

docs: add docs for docs.ollama.com (#12805 )

2025-10-28 13:18:48 -07:00

ollama.png

docs: add docs for docs.ollama.com (#12805 )

2025-10-28 13:18:48 -07:00

openapi.yaml

Report cached prompt tokens (#17943 )

2026-09-02 09:30:44 -07:00

quickstart.mdx

docs: redesign docs landing and integrations overview (#16807 )

2026-06-24 16:28:28 -04:00

README.md

docs: fix broken links (#17676 )

2026-08-11 14:36:39 -07:00

styling.css

docs: collapsed previous retirements (#17167 )

2026-07-14 14:00:10 -07:00

template.mdx

docs: add docs for docs.ollama.com (#12805 )

2025-10-28 13:18:48 -07:00

troubleshooting.mdx

docs: fix broken links (#17676 )

2026-08-11 14:36:39 -07:00

windows.mdx

CUDA: require driver 550 or newer for v12 (#16895 )

2026-06-25 08:46:00 -07:00

README.md

Documentation

Getting Started

Reference

Resources