12 Commits
Author SHA1 Message Date
Alvaro Bartolome 40dfce644a Skip {% generation %} and {% endgeneration %} template handling (#3204)
* Add `.DS_Store` file to `.gitignore`

* Skip `{% generation %}` and `{% endgeneration %}`

Custom syntax within the chat template for the Phi4 Reasoning models
e.g. https://huggingface.co/microsoft/Phi-4-reasoning-plus, which is
AFAIK not handled natively yet, so skipping for now

* Update explanation on `{% generation %}` and `{% endgeneration %}` removal

* Revert "Add `.DS_Store` file to `.gitignore`"

This reverts commit d64d6d2f7f.
2025-05-01 12:13:17 +02:00
Alvaro Bartolome 95ccba3705 Bump sccache to 0.10.0 (#3179)
* Ensure that `sccache` version is 0.10.0 or higher

* Rename `ACTIONS_CACHE_URL` to `ACTIONS_RESULTS_URL`
2025-04-18 12:45:32 +02:00
Alvaro Bartolome 55a6618434 Update --max-batch-total-tokens description (#3083)
* Update `--max-batch-total-tokens` description

* Update docstring in `launcher/src/main.rs` instead
2025-03-07 14:24:26 +01:00
Alvaro Bartolome 8a1cfd6122 Add loop_controls feature to minijinja to handle {% break %} (#2998)
* Add `loop_controls` feature to `minijinja`

* Add `test_chat_template_loop_controls` to test `break`
2025-02-18 10:33:22 +01:00
Alvaro Bartolome 88fd56f549 Add strftime_now callable function for minijinja chat templates (#2983)
* Add `chrono` and `strftime_now` function callable

* Fix `test_chat_template_valid_with_strftime_now`

* Fix `test_chat_template_valid_with_strftime_now`
2025-02-03 15:30:48 +01:00
Alvaro Bartolome 6ab02931cf Set alias for max_completion_tokens in ChatRequest (#2932) 2025-01-23 14:18:47 +01:00
Alvaro Bartolome 64a33c1f05 Run pre-commit run --all-files to fix CI (#2933) 2025-01-21 17:33:33 +01:00
Alvaro BartolomeandDaniël de Kok dc9b8e9814 Fix docker run in README.md (#2861)
* Fix `docker run` in `README.md`

* Add line-break in `docker run` for readability

Co-authored-by: Daniël de Kok <[email protected]>

* Add line-break in `docker run` for readability

Co-authored-by: Daniël de Kok <[email protected]>

---------

Co-authored-by: Daniël de Kok <[email protected]>
2025-01-15 16:07:10 +01:00
Alvaro Bartolome ffe05ccd05 Rollback to ChatRequest for Vertex AI Chat instead of VertexChat (#2651)
As spotted by @philschmid, the payload was compliant with Vertex AI, but
just partially, since ideally the most compliant version would be with
the generation kwargs flattened to be on the same level as the
`messages`; meaning that Vertex AI would still expect a list of
instances, but each instance would be an OpenAI-compatible instance,
which is more clear; and more aligned with the SageMaker integration
too, so kudos to him for spotting that; and sorry from my end for any
inconvenience @Narsil.
2024-10-15 18:11:59 +02:00
Alvaro Bartolome 0aa66d693a Fix build with --features google (#2566)
* Fix `cargo build --features google`

* Add `cargo test --features google`
2024-09-26 11:41:38 +02:00
Alvaro Bartolome 0b7df77178 Add LoRA adapters support for Gemma2 (#2567)
* Add LoRA adapters support for Gemma2

* Make `black` formatting happy
2024-09-26 10:54:08 +02:00
Alvaro Bartolome d31a6f75cc Remove duplicated RUN in Dockerfile (#2547) 2024-09-24 10:19:13 +02:00