GitLab

Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>

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

Signed-off-by: julienmancuso <161955438+julienmancuso@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

Signed-off-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
Co-authored-by: Neelay Shah <neelays@nvidia.com>

Co-authored-by: Anna Tchernych <atchernych@nvidia.com>

Signed-off-by: Shuaiyi Zhang <zhangsy28@lenovo.com>
Co-authored-by: Shuaiyi Zhang <zhangsy28@lenovo.com>
Co-authored-by: Yan Ru Pei <yanrpei@gmail.com>

Signed-off-by: Akash <akpaul@nvidia.com>

Signed-off-by: Hyogeun Oh <ohg3417@gmail.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>

Example:
```
dynamo-run out=<engine> <model> --kv-cache-block-size 64
```

In a distributed system this goes on the worker node and is propagated to ingress via the model deployment card.

Previously hard coded to 16, which is now the default.

- Load context_length from model. Closes #1172
- Store context length and KV cache block size in Model Deployment Card #1170

Co-authored-by: root <root@kkranen-dt.nvidia.com>

Removed the hard coded sleeps, explained what we're testing.

Closes https://github.com/ai-dynamo/dynamo/issues/1132

The race condition is that `apply_event` sends a message on a channel, it does not directly apply the event. At some later point the tokio runtime schedules the task running the channel receiver, which applies the event. If that had not happened yet the test would fail.

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.