.gitignore
LICENSE
MANIFEST.in
Makefile
README.md
pyproject.toml
requirements.txt
setup.cfg
.github/pull_request_template.md
.github/workflows/check_code_quality.yml
.github/workflows/doc-build.yml
.github/workflows/doc-pr-build.yml
.github/workflows/pypi-release.yaml
.github/workflows/secrets-leak.yml
.github/workflows/test-pytorch-xla-tpu-tgi-jetstream.yml
.github/workflows/test-pytorch-xla-tpu-tgi-nightly-jetstream.yml
.github/workflows/test-pytorch-xla-tpu-tgi-nightly.yml
.github/workflows/test-pytorch-xla-tpu-tgi.yml
.github/workflows/test-pytorch-xla-tpu.yml
.github/workflows/tpu-tgi-release.yml
.github/workflows/upload_pr_documentation.yml
docs/source/_toctree.yml
docs/source/index.mdx
docs/source/howto/deploy.mdx
docs/source/howto/overview.mdx
docs/source/howto/serving.mdx
docs/source/howto/training.mdx
docs/source/tutorials/overview.mdx
examples/README.md
examples/language-modeling/gemma_tuning.ipynb
examples/language-modeling/llama_tuning.ipynb
examples/text-generation/generation.py
optimum/tpu/__init__.py
optimum/tpu/cli.py
optimum/tpu/distributed_model.py
optimum/tpu/fsdp_v2.py
optimum/tpu/jetstream_pt_support.py
optimum/tpu/model.py
optimum/tpu/modeling.py
optimum/tpu/modeling_gemma.py
optimum/tpu/modeling_llama.py
optimum/tpu/modeling_mistral.py
optimum/tpu/static_cache_xla.py
optimum/tpu/version.py
optimum/tpu/xla_logger.py
optimum/tpu/xla_model_parallel.py
optimum/tpu/xla_mp_comm.py
optimum/tpu/generation/__init__.py
optimum/tpu/generation/logits_process.py
optimum/tpu/generation/token_selector.py
optimum_tpu.egg-info/PKG-INFO
optimum_tpu.egg-info/SOURCES.txt
optimum_tpu.egg-info/dependency_links.txt
optimum_tpu.egg-info/entry_points.txt
optimum_tpu.egg-info/requires.txt
optimum_tpu.egg-info/top_level.txt
tests/conftest.py
tests/test_distributed_model.py
text-generation-inference/README.md
text-generation-inference/docker/Dockerfile
text-generation-inference/docker/entrypoint.sh
text-generation-inference/integration-tests/conftest.py
text-generation-inference/integration-tests/pytest.ini
text-generation-inference/integration-tests/requirements.txt
text-generation-inference/integration-tests/test_model.py
text-generation-inference/server/Makefile
text-generation-inference/server/build-requirements.txt
text-generation-inference/server/pyproject.toml
text-generation-inference/server/text_generation_server/auto_generator.py
text-generation-inference/server/text_generation_server/cli.py
text-generation-inference/server/text_generation_server/generator.py
text-generation-inference/server/text_generation_server/generator_base.py
text-generation-inference/server/text_generation_server/interceptor.py
text-generation-inference/server/text_generation_server/server.py
text-generation-inference/server/text_generation_server/version.py
text-generation-inference/server/text_generation_server/jetstream_pt_support/__init__.py
text-generation-inference/server/text_generation_server/jetstream_pt_support/compatibility.py
text-generation-inference/server/text_generation_server/jetstream_pt_support/engine_loader.py
text-generation-inference/server/text_generation_server/jetstream_pt_support/generator.py
text-generation-inference/server/text_generation_server/jetstream_pt_support/logits_process.py
text-generation-inference/server/text_generation_server/jetstream_pt_support/token_selector.py
text-generation-inference/server/text_generation_server/jetstream_pt_support/models/__init__.py
text-generation-inference/server/text_generation_server/jetstream_pt_support/models/gemma_model_hf.py
text-generation-inference/server/text_generation_server/jetstream_pt_support/models/llama_model_exportable_hf.py
text-generation-inference/server/text_generation_server/jetstream_pt_support/models/mixtral_model_hf.py
text-generation-inference/tests/conftest.py
text-generation-inference/tests/decode_tests_utils.py
text-generation-inference/tests/helpers.py
text-generation-inference/tests/pytest.ini
text-generation-inference/tests/test_decode.py
text-generation-inference/tests/test_decode_jetstream.py
text-generation-inference/tests/test_decode_jetstream_quant.py
text-generation-inference/tests/test_generator_slot.py
text-generation-inference/tests/test_prefill_truncate.py
text-generation-inference/tests/test_tinyllama.py
text-generation-inference/tests/test_warmup.py