GitLab

Signed-off-by: Graham King <grahamk@nvidia.com>

Signed-off-by: Graham King <grahamk@nvidia.com>

Signed-off-by: Graham King <grahamk@nvidia.com>

Signed-off-by: PeaBrane <yanrpei@gmail.com>

Signed-off-by: mohammedabdulwahhab <furkhan324@berkeley.edu>

Signed-off-by: Jacky <18255193+kthui@users.noreply.github.com>

Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>

Signed-off-by: Graham King <grahamk@nvidia.com>

Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Signed-off-by: hongkuan <hongkuanz@nvidia.com>

Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>

Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>

Signed-off-by: Tzu-Ling Kan <tzulingk@nvidia.com>

Signed-off-by: Ryan Olson <rolson@nvidia.com>
Co-authored-by: Olga Andreeva <oandreeva@nvidia.com>
Co-authored-by: Ziqi Fan <ziqif@nvidia.com>
Co-authored-by: John Thompson <jothomson@nvidia.com>
Co-authored-by: Richard Huo <rihuo@nvidia.com>
Co-authored-by: Zicheng Ma <zichengm@nvidia.com>

Signed-off-by: nachiketb-nvidia <nachiketb@nvidia.com>

Signed-off-by: jthomson04 <jwillthomson19@gmail.com>

Signed-off-by: Neelay Shah <neelays@nvidia.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: Olga Andreeva <124622579+oandreeva-nv@users.noreply.github.com>

Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com>
Co-authored-by: Jacky <18255193+kthui@users.noreply.github.com>
Co-authored-by: hhzhang16 <54051230+hhzhang16@users.noreply.github.com>

Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>

Signed-off-by: Michael Feil <63565275+michaelfeil@users.noreply.github.com>
Co-authored-by: Michael Feil <63565275+michaelfeil@users.noreply.github.com>
Co-authored-by: jthomson04 <jwillthomson19@gmail.com>
Co-authored-by: Ryan Olson <ryanolson@users.noreply.github.com>

Llama 4 has a very large context length (aka n_ctx, model_max_length, max_model_len), and vllm won't start unless it can allocate enough KV cache for the entire context.

Allow passing `--context-length <N>` to `dynamo-run` to limit it so long-context models will fit.

Future todo:
- Restrict every request's `max_tokens` to below the context length. Our pre-processor should do this by setting stop_conditions.max_tokens. mistralrs engine wrapper must do it itself because it does not use the pre-processor.
- mistralrs and llamacpp currently have a hard-coded max context length if one is not provided on the command line. Change those to be the model's built-in max, read from the GGUF or tokenizer_config.json.