Path	Lines of Code
CODE_OF_CONDUCT.md	97
CONTRIBUTING.md	80
README.md	252
assets/tgi_grafana.json	3999
backends/gaudi/README.md	122
backends/gaudi/examples/docker_commands/docker_commands.md	245
backends/gaudi/server/README.md	10
backends/gaudi/server/requirements.txt	86
backends/llamacpp/README.md	18
backends/llamacpp/requirements.txt	4
backends/neuron/README.md	16
backends/neuron/server/build-requirements.txt	3
backends/neuron/tests/pytest.ini	2
backends/neuron/tests/requirements.txt	19
backends/trtllm/CMakeLists.txt	97
backends/trtllm/README.md	41
benchmark/README.md	19
clients/python/README.md	230
crate-hashes.json	3
integration-tests/models/__snapshots__/test_bloom_560m/test_bloom_560m.json	129
integration-tests/models/__snapshots__/test_bloom_560m/test_bloom_560m_all_params.json	99
integration-tests/models/__snapshots__/test_bloom_560m/test_bloom_560m_load.json	514
integration-tests/models/__snapshots__/test_bloom_560m_sharded/test_bloom_560m_sharded.json	129
integration-tests/models/__snapshots__/test_bloom_560m_sharded/test_bloom_560m_sharded_load.json	514
integration-tests/models/__snapshots__/test_chat_llama/test_flash_llama_simple.json	26
integration-tests/models/__snapshots__/test_completion_prompts/test_chat_hfhub_nousage.json	62
integration-tests/models/__snapshots__/test_completion_prompts/test_chat_hfhub_usage.json	75
integration-tests/models/__snapshots__/test_completion_prompts/test_chat_openai_nousage.json	71
integration-tests/models/__snapshots__/test_completion_prompts/test_chat_openai_usage.json	87
integration-tests/models/__snapshots__/test_completion_prompts/test_flash_llama_completion_many_prompts.json	38
integration-tests/models/__snapshots__/test_completion_prompts/test_flash_llama_completion_many_prompts_stream.json	666
integration-tests/models/__snapshots__/test_completion_prompts/test_flash_llama_completion_single_prompt.json	20
integration-tests/models/__snapshots__/test_completion_prompts/test_flash_llama_completion_stream_usage.json	215
integration-tests/models/__snapshots__/test_compressed_tensors_w8a8_int/test_compressed_tensors_w8a8_int.json	73
integration-tests/models/__snapshots__/test_compressed_tensors_w8a8_int/test_compressed_tensors_w8a8_int_all_params.json	73
integration-tests/models/__snapshots__/test_compressed_tensors_w8a8_int/test_compressed_tensors_w8a8_int_load.json	294
integration-tests/models/__snapshots__/test_compressed_tensors_w8a8_int_dynamic_weight/test_compressed_tensors_w8a8_int_dynamic_weight.json	469
integration-tests/models/__snapshots__/test_compressed_tensors_w8a8_int_dynamic_weight/test_compressed_tensors_w8a8_int_dynamic_weight_all_params.json	73
integration-tests/models/__snapshots__/test_compressed_tensors_w8a8_int_dynamic_weight/test_compressed_tensors_w8a8_int_dynamic_weight_load.json	294
integration-tests/models/__snapshots__/test_compressed_tensors_w8an_fp/test_compressed_tensors_w8an.json	73
integration-tests/models/__snapshots__/test_compressed_tensors_w8an_fp/test_compressed_tensors_w8an_all_params.json	73
integration-tests/models/__snapshots__/test_compressed_tensors_w8an_fp/test_compressed_tensors_w8an_load.json	294
integration-tests/models/__snapshots__/test_compressed_tensors_wna16_int/test_compressed_tensors_wna16.json	73
integration-tests/models/__snapshots__/test_compressed_tensors_wna16_int/test_compressed_tensors_wna16_all_params.json	73
integration-tests/models/__snapshots__/test_compressed_tensors_wna16_int/test_compressed_tensors_wna16_load.json	294
integration-tests/models/__snapshots__/test_compressed_tensors_wna16_int_24/test_compressed_tensors_wna16_int_24.json	73
integration-tests/models/__snapshots__/test_compressed_tensors_wna16_int_24/test_compressed_tensors_wna16_int_24_all_params.json	73
integration-tests/models/__snapshots__/test_compressed_tensors_wna16_int_24/test_compressed_tensors_wna16_int_24_load.json	294
integration-tests/models/__snapshots__/test_continue_final_message/test_llama_completion_single_prompt.json	23
integration-tests/models/__snapshots__/test_continue_final_message/test_llama_completion_single_prompt_continue.json	23
integration-tests/models/__snapshots__/test_flash_awq/test_flash_llama_awq.json	73
integration-tests/models/__snapshots__/test_flash_awq/test_flash_llama_awq_all_params.json	73
integration-tests/models/__snapshots__/test_flash_awq/test_flash_llama_awq_load.json	294
integration-tests/models/__snapshots__/test_flash_awq_sharded/test_flash_llama_awq_load_sharded.json	294
integration-tests/models/__snapshots__/test_flash_awq_sharded/test_flash_llama_awq_sharded.json	73
integration-tests/models/__snapshots__/test_flash_deepseek_v2/test_flash_deepseek_v2.json	73
integration-tests/models/__snapshots__/test_flash_deepseek_v2/test_flash_deepseek_v2_all_params.json	37
integration-tests/models/__snapshots__/test_flash_deepseek_v2/test_flash_deepseek_v2_load.json	294
integration-tests/models/__snapshots__/test_flash_falcon/test_flash_falcon.json	72
integration-tests/models/__snapshots__/test_flash_falcon/test_flash_falcon_all_params.json	72
integration-tests/models/__snapshots__/test_flash_falcon/test_flash_falcon_load.json	290
integration-tests/models/__snapshots__/test_flash_gemma/test_flash_gemma_all_params.json	73
integration-tests/models/__snapshots__/test_flash_gemma/test_flash_gemma_load.json	294
integration-tests/models/__snapshots__/test_flash_gemma/test_flash_gemma_simple.json	73
integration-tests/models/__snapshots__/test_flash_gemma2/test_flash_gemma2.json	73
integration-tests/models/__snapshots__/test_flash_gemma2/test_flash_gemma2_load.json	294
integration-tests/models/__snapshots__/test_flash_gemma3/test_exceed_window.json	109
integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3.json	613
integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_base64_rgb_jpg.json	26
integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_base64_rgb_png.json	26
integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_base64_rgba.json	26
integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_cow.json	26
integration-tests/models/__snapshots__/test_flash_gemma3/test_flash_gemma3_image_cow_dog.json	26
integration-tests/models/__snapshots__/test_flash_gemma_gptq/test_flash_gemma_gptq.json	73
integration-tests/models/__snapshots__/test_flash_gemma_gptq/test_flash_gemma_gptq_all_params.json	73
integration-tests/models/__snapshots__/test_flash_gemma_gptq/test_flash_gemma_gptq_load.json	294
integration-tests/models/__snapshots__/test_flash_gpt2/test_flash_gpt2.json	73
integration-tests/models/__snapshots__/test_flash_gpt2/test_flash_gpt2_load.json	294
integration-tests/models/__snapshots__/test_flash_grammar_llama/test_flash_llama_grammar.json	73
integration-tests/models/__snapshots__/test_flash_grammar_llama/test_flash_llama_grammar_json.json	193
integration-tests/models/__snapshots__/test_flash_grammar_llama/test_flash_llama_grammar_load.json	294
integration-tests/models/__snapshots__/test_flash_grammar_llama/test_flash_llama_grammar_regex.json	73
integration-tests/models/__snapshots__/test_flash_grammar_llama/test_flash_llama_grammar_single_load_instance.json	73
integration-tests/models/__snapshots__/test_flash_llama/test_flash_llama_all_params.json	43
integration-tests/models/__snapshots__/test_flash_llama/test_flash_llama_load.json	294
integration-tests/models/__snapshots__/test_flash_llama/test_flash_llama_simple.json	73
integration-tests/models/__snapshots__/test_flash_llama_exl2/test_flash_llama_exl2.json	73
integration-tests/models/__snapshots__/test_flash_llama_exl2/test_flash_llama_exl2_all_params.json	73
integration-tests/models/__snapshots__/test_flash_llama_exl2/test_flash_llama_exl2_load.json	294
integration-tests/models/__snapshots__/test_flash_llama_fp8/test_flash_llama_fp8.json	73
integration-tests/models/__snapshots__/test_flash_llama_fp8/test_flash_llama_fp8_all_params.json	73
integration-tests/models/__snapshots__/test_flash_llama_fp8/test_flash_llama_fp8_load.json	294
integration-tests/models/__snapshots__/test_flash_llama_fp8_kv_cache/test_flash_llama_fp8_kv_cache.json	73
integration-tests/models/__snapshots__/test_flash_llama_fp8_kv_cache/test_flash_llama_fp8_kv_cache_all_params.json	73
integration-tests/models/__snapshots__/test_flash_llama_fp8_kv_cache/test_flash_llama_fp8_kv_cache_load.json	294
integration-tests/models/__snapshots__/test_flash_llama_gptq/test_flash_llama_gptq.json	73
integration-tests/models/__snapshots__/test_flash_llama_gptq/test_flash_llama_gptq_all_params.json	73
integration-tests/models/__snapshots__/test_flash_llama_gptq/test_flash_llama_gptq_load.json	294
integration-tests/models/__snapshots__/test_flash_llama_marlin/test_flash_llama_marlin.json	73
integration-tests/models/__snapshots__/test_flash_llama_marlin/test_flash_llama_marlin_all_params.json	73
integration-tests/models/__snapshots__/test_flash_llama_marlin/test_flash_llama_marlin_load.json	294
integration-tests/models/__snapshots__/test_flash_llama_marlin_24/test_flash_llama_marlin.json	73
integration-tests/models/__snapshots__/test_flash_llama_marlin_24/test_flash_llama_marlin24_all_params.json	73
integration-tests/models/__snapshots__/test_flash_llama_marlin_24/test_flash_llama_marlin24_load.json	294
integration-tests/models/__snapshots__/test_flash_llama_prefix/test_flash_llama_load.json	2550
integration-tests/models/__snapshots__/test_flash_llama_prefix_flashdecoding/test_flash_llama_flashdecoding.json	2550
integration-tests/models/__snapshots__/test_flash_medusa/test_flash_medusa_all_params.json	72
integration-tests/models/__snapshots__/test_flash_medusa/test_flash_medusa_load.json	290
integration-tests/models/__snapshots__/test_flash_medusa/test_flash_medusa_simple.json	72
integration-tests/models/__snapshots__/test_flash_mistral/test_flash_mistral.json	73
integration-tests/models/__snapshots__/test_flash_mistral/test_flash_mistral_all_params.json	73
integration-tests/models/__snapshots__/test_flash_mistral/test_flash_mistral_load.json	294
integration-tests/models/__snapshots__/test_flash_mixtral/test_flash_mixtral.json	73
integration-tests/models/__snapshots__/test_flash_mixtral/test_flash_mixtral_all_params.json	73
integration-tests/models/__snapshots__/test_flash_mixtral/test_flash_mixtral_load.json	294
integration-tests/models/__snapshots__/test_flash_mixtral_awq/test_flash_mixtral_awq.json	73
integration-tests/models/__snapshots__/test_flash_mixtral_awq/test_flash_mixtral_awq_all_params.json	73
integration-tests/models/__snapshots__/test_flash_mixtral_awq/test_flash_mixtral_awq_load.json	294
integration-tests/models/__snapshots__/test_flash_mixtral_gptq/test_flash_mixtral_gptq.json	73
integration-tests/models/__snapshots__/test_flash_mixtral_gptq/test_flash_mixtral_gptq_all_params.json	73
integration-tests/models/__snapshots__/test_flash_mixtral_gptq/test_flash_mixtral_gptq_load.json	294
integration-tests/models/__snapshots__/test_flash_neox/test_flash_neox.json	72
integration-tests/models/__snapshots__/test_flash_neox/test_flash_neox_load.json	290
integration-tests/models/__snapshots__/test_flash_neox_sharded/test_flash_neox.json	72
integration-tests/models/__snapshots__/test_flash_neox_sharded/test_flash_neox_load.json	290
integration-tests/models/__snapshots__/test_flash_pali_gemma/test_flash_pali_gemma.json	25
integration-tests/models/__snapshots__/test_flash_pali_gemma/test_flash_pali_gemma_two_images.json	61
integration-tests/models/__snapshots__/test_flash_pali_gemma2/test_flash_pali_gemma_image.json	133
integration-tests/models/__snapshots__/test_flash_phi/test_flash_phi.json	73
integration-tests/models/__snapshots__/test_flash_phi/test_flash_phi_all_params.json	49
integration-tests/models/__snapshots__/test_flash_phi/test_flash_phi_load.json	294
integration-tests/models/__snapshots__/test_flash_phi35_moe/test_flash_phi35_moe.json	73
integration-tests/models/__snapshots__/test_flash_phi35_moe/test_flash_phi35_moe_all_params.json	73
integration-tests/models/__snapshots__/test_flash_phi35_moe/test_flash_phi35_moe_load.json	294
integration-tests/models/__snapshots__/test_flash_qwen2/test_flash_qwen2.json	73
integration-tests/models/__snapshots__/test_flash_qwen2/test_flash_qwen2_all_params.json	73
integration-tests/models/__snapshots__/test_flash_qwen2/test_flash_qwen2_load.json	294
integration-tests/models/__snapshots__/test_flash_qwen2_5_vl/test_flash_qwen2_5_vl_bay.json	26
integration-tests/models/__snapshots__/test_flash_qwen2_5_vl/test_flash_qwen2_5_vl_simple.json	26
integration-tests/models/__snapshots__/test_flash_qwen2_5_vl/test_flash_qwen2_5_vl_simple_streaming.json	20
integration-tests/models/__snapshots__/test_flash_qwen2_vl/test_flash_qwen2_vl_bay.json	26
integration-tests/models/__snapshots__/test_flash_qwen2_vl/test_flash_qwen2_vl_inpaint.json	26
integration-tests/models/__snapshots__/test_flash_qwen2_vl/test_flash_qwen2_vl_simple.json	26
integration-tests/models/__snapshots__/test_flash_qwen2_vl/test_flash_qwen2_vl_simple_streaming.json	20
integration-tests/models/__snapshots__/test_flash_santacoder/test_flash_santacoder.json	72
integration-tests/models/__snapshots__/test_flash_santacoder/test_flash_santacoder_load.json	290
integration-tests/models/__snapshots__/test_flash_starcoder/test_flash_starcoder.json	72
integration-tests/models/__snapshots__/test_flash_starcoder/test_flash_starcoder_default_params.json	373
integration-tests/models/__snapshots__/test_flash_starcoder/test_flash_starcoder_load.json	290
integration-tests/models/__snapshots__/test_flash_starcoder2/test_flash_starcoder2.json	73
integration-tests/models/__snapshots__/test_flash_starcoder2/test_flash_starcoder2_default_params.json	373
integration-tests/models/__snapshots__/test_flash_starcoder2/test_flash_starcoder2_load.json	294
integration-tests/models/__snapshots__/test_flash_starcoder2_lora/test_flash_starcoder2.json	73
integration-tests/models/__snapshots__/test_flash_starcoder2_lora/test_flash_starcoder2_default_params.json	373
integration-tests/models/__snapshots__/test_flash_starcoder2_lora/test_flash_starcoder2_load.json	294
integration-tests/models/__snapshots__/test_flash_starcoder2_lora/test_flash_starcoder2_with_hugcode_adapter.json	71
integration-tests/models/__snapshots__/test_flash_starcoder_gptq/test_flash_starcoder_gptq.json	25
integration-tests/models/__snapshots__/test_flash_starcoder_gptq/test_flash_starcoder_gptq_default_params.json	25
integration-tests/models/__snapshots__/test_flash_starcoder_gptq/test_flash_starcoder_gptq_load.json	102
integration-tests/models/__snapshots__/test_grammar_llama/test_non_flash_llama_grammar_json.json	193
integration-tests/models/__snapshots__/test_grammar_response_format_llama/test_grammar_response_format_llama_json.1.json	23
integration-tests/models/__snapshots__/test_grammar_response_format_llama/test_grammar_response_format_llama_json.2.json	23
integration-tests/models/__snapshots__/test_grammar_response_format_llama/test_grammar_response_format_llama_json.json	23
integration-tests/models/__snapshots__/test_idefics/test_idefics.json	168
integration-tests/models/__snapshots__/test_idefics/test_idefics_load.json	674
integration-tests/models/__snapshots__/test_idefics/test_idefics_two_images.json	91
integration-tests/models/__snapshots__/test_idefics2/test_flash_idefics2_next_all_params.json	73
integration-tests/models/__snapshots__/test_idefics2/test_flash_idefics2_next_load.json	294
integration-tests/models/__snapshots__/test_idefics2/test_flash_idefics2_next_simple.json	73
integration-tests/models/__snapshots__/test_idefics2/test_flash_idefics2_two_images.json	127
integration-tests/models/__snapshots__/test_idefics3/test_flash_idefics3_next_simple_url.json	67
integration-tests/models/__snapshots__/test_json_schema_constrain/test_json_schema_basic.json	23
integration-tests/models/__snapshots__/test_json_schema_constrain/test_json_schema_complex.json	23
integration-tests/models/__snapshots__/test_json_schema_constrain/test_json_schema_stream.json	743
integration-tests/models/__snapshots__/test_llava_next/test_flash_llava_next_all_params.json	49
integration-tests/models/__snapshots__/test_llava_next/test_flash_llava_next_load.json	294
integration-tests/models/__snapshots__/test_llava_next/test_flash_llava_next_simple.json	73
integration-tests/models/__snapshots__/test_lora_mistral/test_lora_mistral_with_customer_support_adapter.json	251
integration-tests/models/__snapshots__/test_lora_mistral/test_lora_mistral_with_dbpedia_adapter.json	53
integration-tests/models/__snapshots__/test_lora_mistral/test_lora_mistral_without_adapter.json	251
integration-tests/models/__snapshots__/test_lora_mistral/test_lora_mistral_without_customer_support_adapter.json	251
integration-tests/models/__snapshots__/test_mamba/test_mamba.json	73
integration-tests/models/__snapshots__/test_mamba/test_mamba_all_params.json	99
integration-tests/models/__snapshots__/test_mamba/test_mamba_load.json	398
integration-tests/models/__snapshots__/test_mllama/test_mllama_load.json	54
integration-tests/models/__snapshots__/test_mllama/test_mllama_simpl.json	26
integration-tests/models/__snapshots__/test_mpt/test_mpt.json	140
integration-tests/models/__snapshots__/test_mpt/test_mpt_load.json	562
integration-tests/models/__snapshots__/test_mt0_base/test_mt0_base.json	48
integration-tests/models/__snapshots__/test_mt0_base/test_mt0_base_all_params.json	79
integration-tests/models/__snapshots__/test_mt0_base/test_mt0_base_load.json	218
integration-tests/models/__snapshots__/test_neox/test_neox.json	72
integration-tests/models/__snapshots__/test_neox/test_neox_load.json	290
integration-tests/models/__snapshots__/test_neox_sharded/test_neox.json	72
integration-tests/models/__snapshots__/test_neox_sharded/test_neox_load.json	290
integration-tests/models/__snapshots__/test_server_gptq_quantized/test_server_gptq_quantized.json	73
integration-tests/models/__snapshots__/test_server_gptq_quantized/test_server_gptq_quantized_all_params.json	73
integration-tests/models/__snapshots__/test_server_gptq_quantized/test_server_gptq_quantized_load.json	294
integration-tests/models/__snapshots__/test_smolvlm/test_flash_smolvlm_next_simple_url.json	61
integration-tests/models/__snapshots__/test_t5_sharded/test_t5_sharded.json	60
integration-tests/models/__snapshots__/test_t5_sharded/test_t5_sharded_load.json	242
integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_auto_nostream.json	34
integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_choice_nostream.json	34
integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_choice_stream.json	512
integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_insufficient_information_nostream.json	24
integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_insufficient_information_stream.json	402
integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_nostream.json	34
integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_openai.json	563
integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_sea_creatures_stream_auto.json	402
integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_sea_creatures_stream_function_object.json	1
integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_sea_creatures_stream_none.json	2002
integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_grammar_tools_sea_creatures_stream_required.json	1
integration-tests/models/__snapshots__/test_tools_llama/test_flash_llama_tool_reply_response.json	24
integration-tests/models/__snapshots__/test_transformers_llama4/test_flash_llama4.json	613
integration-tests/models/__snapshots__/test_transformers_llama4/test_flash_llama4_image_base64_rgb_jpg.json	26
integration-tests/models/__snapshots__/test_transformers_llama4/test_flash_llama4_image_base64_rgb_png.json	26
integration-tests/models/__snapshots__/test_transformers_llama4/test_flash_llama4_image_base64_rgba.json	26
integration-tests/models/__snapshots__/test_transformers_llama4/test_flash_llama4_image_cow.json	26
integration-tests/models/__snapshots__/test_transformers_llama4/test_flash_llama4_image_cow_dog.json	26
integration-tests/models/__snapshots__/test_transformers_olmo/test_flash_llama_load.json	294
integration-tests/models/__snapshots__/test_transformers_olmo/test_flash_llama_simple.json	73
integration-tests/pytest.ini	5
integration-tests/requirements.txt	120
router/README.md	65
server/README.md	10
server/req.txt	212
server/requirements_cuda.txt	390
server/requirements_gen.txt	191
server/requirements_intel.txt	386
server/requirements_rocm.txt	386