LICENSE
pyproject.toml
src/inference_glue/__init__.py
src/inference_glue/cli.py
src/inference_glue/config.py
src/inference_glue/endpoint.py
src/inference_glue/model.py
src/inference_glue/model_instance.py
src/inference_glue/observability.py
src/inference_glue/request_context.py
src/inference_glue.egg-info/PKG-INFO
src/inference_glue.egg-info/SOURCES.txt
src/inference_glue.egg-info/dependency_links.txt
src/inference_glue.egg-info/entry_points.txt
src/inference_glue.egg-info/requires.txt
src/inference_glue.egg-info/top_level.txt
src/inference_glue/api_wrappers/__init__.py
src/inference_glue/api_wrappers/llama_cpp_api.py
src/inference_glue/api_wrappers/openai_api.py
src/inference_glue/api_wrappers/openrouter_api.py
src/inference_glue/api_wrappers/vllm_api.py
src/inference_glue/assets/gemma4_tokenizer/chat_template.jinja
src/inference_glue/assets/gemma4_tokenizer/config.json
src/inference_glue/assets/gemma4_tokenizer/generation_config.json
src/inference_glue/assets/gemma4_tokenizer/processor_config.json
src/inference_glue/assets/gemma4_tokenizer/tokenizer.json
src/inference_glue/assets/gemma4_tokenizer/tokenizer_config.json
src/inference_glue/assets/qwen3.5_tokenizer/chat_template.jinja
src/inference_glue/assets/qwen3.5_tokenizer/config.json
src/inference_glue/assets/qwen3.5_tokenizer/merges.txt
src/inference_glue/assets/qwen3.5_tokenizer/preprocessor_config.json
src/inference_glue/assets/qwen3.5_tokenizer/tokenizer.json
src/inference_glue/assets/qwen3.5_tokenizer/tokenizer_config.json
src/inference_glue/assets/qwen3.5_tokenizer/vocab.json
src/inference_glue/chat_templates/__init__.py
src/inference_glue/chat_templates/base.py
src/inference_glue/chat_templates/gemma.py
src/inference_glue/chat_templates/gemma4.py
src/inference_glue/chat_templates/glm.py
src/inference_glue/chat_templates/gpt_oss.py
src/inference_glue/chat_templates/mistral.py
src/inference_glue/chat_templates/qwen.py
src/inference_glue/chat_templates/qwen3_5.py
src/inference_glue/datatypes/__init__.py
src/inference_glue/datatypes/base_data_classes.py
src/inference_glue/datatypes/completion.py
src/inference_glue/datatypes/default_sampling.py
src/inference_glue/datatypes/errors.py
src/inference_glue/datatypes/tools.py
src/inference_glue/datatypes/utils.py
src/inference_glue/model_family/__init__.py
src/inference_glue/model_family/gemma3.py
src/inference_glue/model_family/gemma4.py
src/inference_glue/model_family/qwen3_5.py
src/inference_glue/model_family/qwen3_6.py
src/inference_glue/tokenizer/__init__.py
src/inference_glue/tokenizer/base.py
src/inference_glue/tokenizer/hf_tokenizer.py
src/inference_glue/tokenizer/sp_tokenizer.py
tests/test_chat_templates.py
tests/test_cli.py
tests/test_config.py
tests/test_default_sampling.py
tests/test_model.py
tests/test_model_families.py
tests/test_observability.py
tests/test_request_context.py
tests/test_retry.py
tests/test_thinking.py