relax pydantic version restriction (#1658)

Co-authored-by: dhuangnm <dhuang@MacBook-Pro-2.local>

[TextGeneration] Fix llama tokenizer (#1635) (#1636)

* [TextGeneration] Fix llama tokenizer (#1635)

* add llama tokenizer fix

* fix generated string

* only run for streaming

* add TODO

---------

Co-authored-by: Dipika Sikka <dipikasikka1@gmail.coom>

* Retire `flaky` in favour of `pytest-rerunfailures` (#1628)

* pick up another fix and bump up version to 1.7.1

---------

Co-authored-by: Dipika Sikka <dipikasikka1@gmail.com>
Co-authored-by: Dipika Sikka <dipikasikka1@gmail.coom>
Co-authored-by: dbogunowicz <97082108+dbogunowicz@users.noreply.github.com>
Co-authored-by: dhuang <dhuang@MacBook-Pro-2.local>

[cherry-pick] UPDATE src/deepsparse/image_classification/README.md (#…

…1621) (#1626)

[Cherry-pick] Hotfix 1.6.1 for license changes (#1485)

* Delete LICENSE (#1444)

* Delete LICENSE

* Rename LICENSE-NEURALMAGIC to LICENSE

renaming NM DS License -> License

* Update README.md

Fixed License language

* Update README.md

* Update README.md

fixed top header

* Update NOTICE

* Update setup.py

changed license references - to review w/ @dhuangnm

* pick up license change for hotfix 1.6.1

---------

Co-authored-by: Rob Greenberg <100797996+rgreenberg1@users.noreply.github.com>
Co-authored-by: dhuang <dhuang@MacBook-Pro-2.local>

[Cherry-Pick][Text Generation] Terminate the inference when kv cache …

…is full (#1447)

* [Fix] Remove erronous LIB.kv_cache input when using external kv cache management (#1337)

* initial commit

* initial commit

* cleanup

* cleanup2

* initial commit

* initial commit

* Needs to be >=

bump hotfix version to 1.5.3 (#1184)

Co-authored-by: dhuang <dhuang@MacBook-Pro-2.local>

[cherry-pick 1.5.2] pin pydantic to <2.0 (#1645) (#1107)

* Restrict `pydantic<2.0.0` due to breaking changes (#1104)

> Pydantic V2 is a ground-up rewrite that offers many new features, performance improvements, and some breaking changes compared to Pydantic V1.

```
deepsparse/pipeline.py:822: in <module>
    class PipelineConfig(BaseModel):
...
NameError: Field "model_path" has conflict with protected namespace "model_"
```

* bump version to 1.5.2

---------

Co-authored-by: Michael Goin <michael@neuralmagic.com>

[1.5.1] restrict pandas to <2.0 (#1074)

* [1.5.1] restrict pandas to <2.0

this fixes a bug in the latest NM 1.5 supported transformers datasets that is incompatible with pandas 2.0. Future releases will support later datasets versions

* bump version to 1.5.1

[Cherry Pick] Using system_logging_config directly instead of using D…

…epends (#858) (1.4.2) (#973)

* Using system_logging_config directly instead of using Depends (#858)

* Update version.py

---------

Co-authored-by: corey-nm <109536191+corey-nm@users.noreply.github.com>
Co-authored-by: Benjamin Fineran <bfineran@users.noreply.github.com>

[Cherry Pick] Using system_logging_config directly instead of using D…

…epends (#858) (1.4.2) (#973)

* Using system_logging_config directly instead of using Depends (#858)

* Update version.py

---------

Co-authored-by: corey-nm <109536191+corey-nm@users.noreply.github.com>
Co-authored-by: Benjamin Fineran <bfineran@users.noreply.github.com>