* fix: remove jinja parameter* chore: disable linux arm CI---------Co-authored-by: sangjanai <sang@jan.ai>

* fix: check model is loaded before starting* chore: e2e test---------Co-authored-by: sangjanai <sang@jan.ai>

* refactor: remove --pooling flag from model loadingThe --pooling flag was removed as the mean pooling functionality not needed in chat models. This fixes the regression* feat(local-engine): add ctx_len parameter supportAdds support for the ctx_len parameter by appending --ctx-size with its value. Removed outdated parameter mappings from the kParamsMap to reflect current implementation details and ensure consistency.* feat: add conditional model parameters based on pathWhen the model path contains both "jan" and "nano" (case-insensitive), automatically addspeculative decoding parameters to adjust generation behavior. This improvesflexibility by enabling environment-specific configurations without manualparameter tuning. Also includes necessary headers for string manipulation andfixes whitespace in ctx_len handling.* chore: remove redundant commentThe comment was redundant as the code's purpose is clear without it, improving readability.

…all local models (#2207)Co-authored-by: Ethan Garber <ethancgarber@gmail.com>Co-authored-by: Akarshan Biswas <akarshan@menlo.ai>