path	# lines of code
rust-toolchain.toml	5
load_tests/benchmarks.py	252
load_tests/filter.py	17
load_tests/orca.py	21
load_tests/long.js	50
load_tests/common.js	50
load_tests/pyproject.toml	17
load_tests/long.py	11
load_tests/long_prompt2.py	15
backends/trtllm/scripts/setup_sccache.py	37
backends/trtllm/cmake/utils/detect_cuda_arch.cu	1
backends/trtllm/cmake/trtllm.cmake	40
backends/trtllm/cmake/spdlog.cmake	15
backends/trtllm/cmake/json.cmake	6
backends/trtllm/src/utils.rs	4
backends/trtllm/src/errors.rs	20
backends/trtllm/src/looper.rs	281
backends/trtllm/src/lib.rs	67
backends/trtllm/src/main.rs	296
backends/trtllm/csrc/backend.cpp	59
backends/trtllm/csrc/backend.hpp	133
backends/trtllm/csrc/hardware.hpp	38
backends/trtllm/csrc/ffi.hpp	156
backends/trtllm/Cargo.toml	23
backends/trtllm/build.rs	203
backends/v2/src/client/sharded_client.rs	203
backends/v2/src/client/mod.rs	52
backends/v2/src/client/grpc_client.rs	208
backends/v2/src/queue.rs	527
backends/v2/src/backend.rs	402
backends/v2/src/lib.rs	118
backends/v2/src/main.rs	203
backends/v2/Cargo.toml	70
backends/v2/build.rs	15
backends/neuron/Cargo.toml	42
backends/neuron/server/pyproject.toml	23
backends/neuron/server/text_generation_server/interceptor.py	25
backends/neuron/server/text_generation_server/tgi_env.py	229
backends/neuron/server/text_generation_server/generator.py	501
backends/neuron/server/text_generation_server/cli.py	69
backends/neuron/server/text_generation_server/server.py	69
backends/neuron/server/text_generation_server/model.py	99
backends/neuron/tgi_entry_point.py	34
backends/client/src/v2/client.rs	208
backends/client/src/v2/sharded_client.rs	202
backends/client/src/v2/mod.rs	11
backends/client/src/lib.rs	68
backends/client/src/v3/client.rs	247
backends/client/src/v3/sharded_client.rs	217
backends/client/src/v3/mod.rs	11
backends/client/Cargo.toml	20
backends/client/build.rs	29
backends/grpc-metadata/src/lib.rs	32
backends/grpc-metadata/Cargo.toml	9
backends/llamacpp/src/quantize.rs	30
backends/llamacpp/src/backend.rs	614
backends/llamacpp/src/llamacpp.rs	5
backends/llamacpp/src/main.rs	266
backends/llamacpp/Cargo.toml	20
backends/llamacpp/build.rs	43
backends/gaudi/server/pyproject.toml	38
backends/gaudi/server/text_generation_server/interceptor.py	35
backends/gaudi/server/text_generation_server/tgi_service.py	46
backends/gaudi/server/text_generation_server/utils/debug.py	29
backends/gaudi/server/text_generation_server/utils/dist.py	49
backends/gaudi/server/text_generation_server/utils/__init__.py	47
backends/gaudi/server/text_generation_server/utils/kernels.py	12
backends/gaudi/server/text_generation_server/utils/log.py	11
backends/gaudi/server/text_generation_server/utils/merges/strategies.py	155
backends/gaudi/server/text_generation_server/utils/merges/utils.py	46
backends/gaudi/server/text_generation_server/utils/prefill_chunking.py	15
backends/gaudi/server/text_generation_server/utils/segments.py	38
backends/gaudi/server/text_generation_server/utils/quantization.py	137
backends/gaudi/server/text_generation_server/utils/adapter.py	243
backends/gaudi/server/text_generation_server/utils/sgmv.py	159
backends/gaudi/server/text_generation_server/utils/hub.py	174
backends/gaudi/server/text_generation_server/utils/logits_process.py	402
backends/gaudi/server/text_generation_server/utils/convert.py	82
backends/gaudi/server/text_generation_server/utils/weights.py	295
backends/gaudi/server/text_generation_server/utils/chunks.py	17
backends/gaudi/server/text_generation_server/utils/peft.py	59
backends/gaudi/server/text_generation_server/utils/import_utils.py	11
backends/gaudi/server/text_generation_server/utils/speculate.py	7
backends/gaudi/server/text_generation_server/utils/version.py	27
backends/gaudi/server/text_generation_server/utils/tokens.py	634
backends/gaudi/server/text_generation_server/utils/watermark.py	70
backends/gaudi/server/text_generation_server/models/mllama_causal_lm.py	546
backends/gaudi/server/text_generation_server/models/types.py	82
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_mistral_modeling.py	422
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_santacoder_modeling.py	442
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_gptj_modeling.py	330
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_rw_modeling.py	578
backends/gaudi/server/text_generation_server/models/custom_modeling/bloom_modeling.py	652
backends/gaudi/server/text_generation_server/models/custom_modeling/vlm.py	55
backends/gaudi/server/text_generation_server/models/custom_modeling/__init__.py	1
backends/gaudi/server/text_generation_server/models/custom_modeling/clip.py	466
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_gpt2_modeling.py	366
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_llava_next.py	201
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_llama4_modeling.py	1116
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_qwen3_moe_modeling.py	405
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_phi_moe_modeling.py	134
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_gemma3_modeling.py	629
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_qwen2_modeling.py	333
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_llama_modeling.py	555
backends/gaudi/server/text_generation_server/models/custom_modeling/mamba_modeling.py	207
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_mixtral_modeling.py	422
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_phi_modeling.py	363
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_cohere_modeling.py	422
backends/gaudi/server/text_generation_server/models/custom_modeling/siglip.py	297
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_deepseek_v2_modeling.py	543
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_neox_modeling.py	344
backends/gaudi/server/text_generation_server/models/custom_modeling/idefics3.py	467
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_gemma2_modeling.py	492
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_mllama.py	748
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_gemma_modeling.py	401
backends/gaudi/server/text_generation_server/models/custom_modeling/idefics2.py	677
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_deepseek_v3_modeling.py	604
backends/gaudi/server/text_generation_server/models/custom_modeling/qwen2_5_vl.py	724
backends/gaudi/server/text_generation_server/models/custom_modeling/qwen2_vl.py	429
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_pali_gemma_modeling.py	98
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_qwen3_modeling.py	302
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_dbrx_modeling.py	614
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_starcoder2_modeling.py	515
backends/gaudi/server/text_generation_server/models/__init__.py	984
backends/gaudi/server/text_generation_server/models/flash_vlm_causal_lm.py	856
backends/gaudi/server/text_generation_server/models/flash_causal_lm.py	2113
backends/gaudi/server/text_generation_server/models/globals.py	33
backends/gaudi/server/text_generation_server/models/seq2seq_lm.py	737
backends/gaudi/server/text_generation_server/models/model.py	111
backends/gaudi/server/text_generation_server/__init__.py	1
backends/gaudi/server/text_generation_server/tracing.py	44
backends/gaudi/server/text_generation_server/cache.py	24
backends/gaudi/server/text_generation_server/layers/linear.py	28
backends/gaudi/server/text_generation_server/layers/fp8.py	528
backends/gaudi/server/text_generation_server/layers/medusa.py	144
backends/gaudi/server/text_generation_server/layers/__init__.py	32
backends/gaudi/server/text_generation_server/layers/speculative.py	44
backends/gaudi/server/text_generation_server/layers/bnb.py	93
backends/gaudi/server/text_generation_server/layers/lora.py	197
backends/gaudi/server/text_generation_server/layers/compressed_tensors/__init__.py	2
backends/gaudi/server/text_generation_server/layers/compressed_tensors/loader.py	115
backends/gaudi/server/text_generation_server/layers/compressed_tensors/w8an_fp.py	209
backends/gaudi/server/text_generation_server/layers/tensor_parallel.py	184
backends/gaudi/server/text_generation_server/layers/mlp.py	214
backends/gaudi/server/text_generation_server/layers/rotary.py	507
backends/gaudi/server/text_generation_server/layers/awq/conversion_utils.py	46
backends/gaudi/server/text_generation_server/layers/awq/quantize/__init__.py	2
backends/gaudi/server/text_generation_server/layers/awq/quantize/hpu.py	99
backends/gaudi/server/text_generation_server/layers/exl2.py	52
backends/gaudi/server/text_generation_server/layers/gptq/__init__.py	371
backends/gaudi/server/text_generation_server/layers/gptq/quantize.py	855
backends/gaudi/server/text_generation_server/layers/gptq/utils.py	26
backends/gaudi/server/text_generation_server/layers/gptq/hpu.py	163
backends/gaudi/server/text_generation_server/layers/layernorm.py	45
backends/gaudi/server/text_generation_server/layers/conv.py	33
backends/gaudi/server/text_generation_server/layers/moe/fused_moe.py	97
backends/gaudi/server/text_generation_server/layers/moe/fp8.py	240
backends/gaudi/server/text_generation_server/layers/moe/__init__.py	201
backends/gaudi/server/text_generation_server/layers/moe/unquantized.py	113
backends/gaudi/server/text_generation_server/layers/attention/kv_cache.py	138
backends/gaudi/server/text_generation_server/layers/attention/__init__.py	30
backends/gaudi/server/text_generation_server/layers/attention/hpu.py	178
backends/gaudi/server/text_generation_server/layers/attention/common.py	71
backends/gaudi/server/text_generation_server/cli.py	297
backends/gaudi/server/text_generation_server/adapters/__init__.py	8
backends/gaudi/server/text_generation_server/adapters/lora.py	370
backends/gaudi/server/text_generation_server/adapters/config.py	19
backends/gaudi/server/text_generation_server/adapters/weights.py	101
backends/gaudi/server/text_generation_server/server.py	265
backends/v3/src/radix.rs	741
backends/v3/src/client/sharded_client.rs	207
backends/v3/src/client/mod.rs	50
backends/v3/src/client/grpc_client.rs	255
backends/v3/src/queue.rs	670
backends/v3/src/backend.rs	450
backends/v3/src/lib.rs	159
backends/v3/src/block_allocator.rs	193
backends/v3/src/main.rs	217
backends/v3/benches/prefix_cache.rs	29
backends/v3/Cargo.toml	77
backends/v3/build.rs	15
update_doc.py	149
flake.nix	184
router/src/sagemaker.rs	85
router/src/kserve.rs	228
router/src/chat.rs	641
router/src/config.rs	387
router/src/server.rs	2105
router/src/logging.rs	110
router/src/lib.rs	1176
router/src/validation.rs	1186
router/src/vertex.rs	173
router/src/infer/tool_grammar.rs	99
router/src/infer/mod.rs	89
router/src/usage_stats.rs	369
router/Cargo.toml	73
router/build.rs	18
Cargo.toml	49
launcher/src/gpu.rs	19
launcher/src/env_runtime.rs	58
launcher/src/main.rs	1815
launcher/Cargo.toml	25
launcher/build.rs	19
server/exllama_kernels/exllama_kernels/cuda_buffers.cu	62
server/exllama_kernels/exllama_kernels/tuning.h	9
server/exllama_kernels/exllama_kernels/util.cuh	25
server/exllama_kernels/exllama_kernels/cuda_func/q4_matrix.cu	166
server/exllama_kernels/exllama_kernels/cuda_func/column_remap.cu	50
server/exllama_kernels/exllama_kernels/cuda_func/q4_matmul.cuh	31
server/exllama_kernels/exllama_kernels/cuda_func/column_remap.cuh	15
server/exllama_kernels/exllama_kernels/cuda_func/q4_matrix.cuh	37
server/exllama_kernels/exllama_kernels/cuda_func/q4_matmul.cu	218
server/exllama_kernels/exllama_kernels/cuda_buffers.cuh	40
server/exllama_kernels/exllama_kernels/hip_compat.cuh	45
server/exllama_kernels/exllama_kernels/matrix.cuh	250
server/exllama_kernels/exllama_kernels/cu_compat.cuh	46
server/exllama_kernels/exllama_kernels/exllama_ext.cpp	198
server/exllama_kernels/setup.py	29
server/custom_kernels/custom_kernels/fused_bloom_attention_cuda.cu	219
server/custom_kernels/custom_kernels/fused_attention_cuda.cu	219
server/custom_kernels/setup.py	19
server/pyproject.toml	102
server/text_generation_server/interceptor.py	32
server/text_generation_server/utils/dist.py	80
server/text_generation_server/utils/__init__.py	41
server/text_generation_server/utils/kernels.py	12
server/text_generation_server/utils/log.py	11
server/text_generation_server/utils/merges/strategies.py	155
server/text_generation_server/utils/merges/utils.py	46
server/text_generation_server/utils/prefill_chunking.py	15
server/text_generation_server/utils/segments.py	36
server/text_generation_server/utils/quantization.py	181
server/text_generation_server/utils/adapter.py	250
server/text_generation_server/utils/hub.py	174
server/text_generation_server/utils/logits_process.py	412
server/text_generation_server/utils/convert.py	82
server/text_generation_server/utils/weights.py	290
server/text_generation_server/utils/chunks.py	17
server/text_generation_server/utils/peft.py	59
server/text_generation_server/utils/import_utils.py	59
server/text_generation_server/utils/speculate.py	7
server/text_generation_server/utils/tokens.py	530
server/text_generation_server/utils/watermark.py	70
server/text_generation_server/models/bloom.py	37
server/text_generation_server/models/mllama_causal_lm.py	330
server/text_generation_server/models/types.py	89
server/text_generation_server/models/custom_modeling/idefics_vision.py	347
server/text_generation_server/models/custom_modeling/neox_modeling.py	562
server/text_generation_server/models/custom_modeling/flash_mistral_modeling.py	457
server/text_generation_server/models/custom_modeling/flash_santacoder_modeling.py	444
server/text_generation_server/models/custom_modeling/flash_gptj_modeling.py	327
server/text_generation_server/models/custom_modeling/idefics_config.py	144
server/text_generation_server/models/custom_modeling/flash_rw_modeling.py	583
server/text_generation_server/models/custom_modeling/bloom_modeling.py	652
server/text_generation_server/models/custom_modeling/vlm.py	55
server/text_generation_server/models/custom_modeling/idefics_image_processing.py	145
server/text_generation_server/models/custom_modeling/__init__.py	1
server/text_generation_server/models/custom_modeling/llava_next.py	206
server/text_generation_server/models/custom_modeling/clip.py	466
server/text_generation_server/models/custom_modeling/idefics_processing.py	227
server/text_generation_server/models/custom_modeling/flash_gpt2_modeling.py	372
server/text_generation_server/models/custom_modeling/phi_modeling.py	285
server/text_generation_server/models/custom_modeling/flash_phi_moe_modeling.py	134
server/text_generation_server/models/custom_modeling/flash_gemma3_modeling.py	724
server/text_generation_server/models/custom_modeling/mpt_modeling.py	1105
server/text_generation_server/models/custom_modeling/flash_qwen2_modeling.py	398
server/text_generation_server/models/custom_modeling/gemma3/processing_gemma3.py	137
server/text_generation_server/models/custom_modeling/gemma3/image_processing_gemma3.py	300
server/text_generation_server/models/custom_modeling/gemma3/configuration_gemma3.py	113
server/text_generation_server/models/custom_modeling/gemma3/utils.py	26
server/text_generation_server/models/custom_modeling/flash_llama_modeling.py	581
server/text_generation_server/models/custom_modeling/mamba_modeling.py	207
server/text_generation_server/models/custom_modeling/flash_mixtral_modeling.py	434
server/text_generation_server/models/custom_modeling/flash_phi_modeling.py	354
server/text_generation_server/models/custom_modeling/flash_cohere_modeling.py	448
server/text_generation_server/models/custom_modeling/siglip.py	297
server/text_generation_server/models/custom_modeling/flash_deepseek_v2_modeling.py	561
server/text_generation_server/models/custom_modeling/opt_modeling.py	610
server/text_generation_server/models/custom_modeling/flash_neox_modeling.py	339
server/text_generation_server/models/custom_modeling/idefics3.py	468
server/text_generation_server/models/custom_modeling/flash_gemma2_modeling.py	476
server/text_generation_server/models/custom_modeling/flash_gemma_modeling.py	393
server/text_generation_server/models/custom_modeling/idefics2.py	678
server/text_generation_server/models/custom_modeling/flash_deepseek_v3_modeling.py	569
server/text_generation_server/models/custom_modeling/qwen2_5_vl.py	748
server/text_generation_server/models/custom_modeling/qwen2_vl.py	454
server/text_generation_server/models/custom_modeling/idefics_modeling.py	1048
server/text_generation_server/models/custom_modeling/flash_pali_gemma_modeling.py	101
server/text_generation_server/models/custom_modeling/mllama.py	826
server/text_generation_server/models/custom_modeling/t5_modeling.py	934
server/text_generation_server/models/custom_modeling/flash_dbrx_modeling.py	632
server/text_generation_server/models/custom_modeling/idefics_perceiver.py	166
server/text_generation_server/models/custom_modeling/flash_starcoder2_modeling.py	526
server/text_generation_server/models/__init__.py	1742
server/text_generation_server/models/transformers_flash_vlm.py	499
server/text_generation_server/models/metadata_kernels.py	250
server/text_generation_server/models/idefics_causal_lm.py	708
server/text_generation_server/models/transformers_flash_causal_lm.py	237
server/text_generation_server/models/flash_causal_lm.py	2009
server/text_generation_server/models/causal_lm.py	713
server/text_generation_server/models/vlm_causal_lm.py	931
server/text_generation_server/models/globals.py	57
server/text_generation_server/models/galactica.py	104
server/text_generation_server/models/seq2seq_lm.py	751
server/text_generation_server/models/mamba.py	667
server/text_generation_server/models/model.py	146
server/text_generation_server/__init__.py	1
server/text_generation_server/tracing.py	44
server/text_generation_server/cache.py	24
server/text_generation_server/layers/eetq.py	37
server/text_generation_server/layers/linear.py	104
server/text_generation_server/layers/fp8.py	452
server/text_generation_server/layers/medusa.py	144
server/text_generation_server/layers/__init__.py	30
server/text_generation_server/layers/marlin/util.py	104
server/text_generation_server/layers/marlin/fp8.py	99
server/text_generation_server/layers/marlin/__init__.py	14
server/text_generation_server/layers/marlin/gptq.py	390
server/text_generation_server/layers/marlin/marlin.py	279
server/text_generation_server/layers/speculative.py	44
server/text_generation_server/layers/bnb.py	93
server/text_generation_server/layers/lora.py	201
server/text_generation_server/layers/compressed_tensors/__init__.py	2
server/text_generation_server/layers/compressed_tensors/wna16_int.py	158
server/text_generation_server/layers/compressed_tensors/wna16_int_24.py	79
server/text_generation_server/layers/compressed_tensors/loader.py	142
server/text_generation_server/layers/compressed_tensors/w8an_fp.py	150
server/text_generation_server/layers/compressed_tensors/w8a8_int.py	196
server/text_generation_server/layers/tensor_parallel.py	196
server/text_generation_server/layers/mlp.py	214
server/text_generation_server/layers/rotary.py	494
server/text_generation_server/layers/awq/conversion_utils.py	46
server/text_generation_server/layers/awq/quantize/ipex.py	39
server/text_generation_server/layers/awq/quantize/__init__.py	6
server/text_generation_server/layers/awq/quantize/cuda.py	29
server/text_generation_server/layers/exl2.py	52
server/text_generation_server/layers/gptq/ipex.py	112
server/text_generation_server/layers/gptq/__init__.py	401
server/text_generation_server/layers/gptq/custom_autotune.py	185
server/text_generation_server/layers/gptq/quantize.py	855
server/text_generation_server/layers/gptq/triton.py	314
server/text_generation_server/layers/gptq/exllama.py	89
server/text_generation_server/layers/gptq/utils.py	26
server/text_generation_server/layers/gptq/exllamav2.py	190
server/text_generation_server/layers/layernorm.py	159
server/text_generation_server/layers/conv.py	33
server/text_generation_server/layers/moe/fp8.py	149
server/text_generation_server/layers/moe/gptq_marlin.py	289
server/text_generation_server/layers/moe/__init__.py	234
server/text_generation_server/layers/moe/unquantized.py	202
server/text_generation_server/layers/moe/fused_moe_ipex.py	43
server/text_generation_server/layers/attention/ipex.py	149
server/text_generation_server/layers/attention/kv_cache.py	265
server/text_generation_server/layers/attention/__init__.py	34
server/text_generation_server/layers/attention/rocm.py	286
server/text_generation_server/layers/attention/flashinfer.py	163
server/text_generation_server/layers/attention/flash_attn_triton.py	649
server/text_generation_server/layers/attention/cuda.py	284
server/text_generation_server/layers/attention/common.py	42
server/text_generation_server/cli.py	301
server/text_generation_server/adapters/__init__.py	8
server/text_generation_server/adapters/lora.py	385
server/text_generation_server/adapters/config.py	19
server/text_generation_server/adapters/weights.py	101
server/text_generation_server/server.py	270
server/bounds-from-nix.py	27
server/exllamav2_kernels/setup.py	27
server/exllamav2_kernels/exllamav2_kernels/cuda/matrix_view.cuh	104
server/exllamav2_kernels/exllamav2_kernels/cuda/q_gemm_kernel_gptq.cuh	231
server/exllamav2_kernels/exllamav2_kernels/cuda/util.cuh	45
server/exllamav2_kernels/exllamav2_kernels/cuda/quant/qdq_3.cuh	146
server/exllamav2_kernels/exllamav2_kernels/cuda/quant/qdq_4.cuh	195
server/exllamav2_kernels/exllamav2_kernels/cuda/quant/qdq_2.cuh	89
server/exllamav2_kernels/exllamav2_kernels/cuda/quant/qdq_8.cuh	29
server/exllamav2_kernels/exllamav2_kernels/cuda/quant/qdq_6.cuh	33
server/exllamav2_kernels/exllamav2_kernels/cuda/quant/qdq_util.cuh	44
server/exllamav2_kernels/exllamav2_kernels/cuda/quant/qdq_5.cuh	184
server/exllamav2_kernels/exllamav2_kernels/cuda/q_matrix.cuh	57
server/exllamav2_kernels/exllamav2_kernels/cuda/compat.cuh	45
server/exllamav2_kernels/exllamav2_kernels/cuda/q_gemm.cuh	31
server/exllamav2_kernels/exllamav2_kernels/cuda/q_matrix.cu	544
server/exllamav2_kernels/exllamav2_kernels/cuda/q_gemm.cu	198
server/exllamav2_kernels/exllamav2_kernels/cuda/q_gemm_kernel.cuh	507
server/exllamav2_kernels/exllamav2_kernels/ext.cpp	115
server/exllamav2_kernels/exllamav2_kernels/config.h	11
server/exllamav2_kernels/exllamav2_kernels/cpp/util.h	10
benchmark/src/table.rs	151
benchmark/src/utils.rs	26
benchmark/src/event.rs	43
benchmark/src/lib.rs	126
benchmark/src/app.rs	464
benchmark/src/generation.rs	186
benchmark/src/main.rs	137
benchmark/Cargo.toml	27
nix/impure-shell.nix	104
nix/overlay.nix	49
nix/server.nix	121
nix/client.nix	18
nix/crate-overrides.nix	85
nix/docker.nix	34
Dockerfile.nix	20
proto/generate.proto	208
proto/v3/generate.proto	258
clients/python/pyproject.toml	26
clients/python/text_generation/client.py	538
clients/python/text_generation/errors.py	61
clients/python/text_generation/types.py	263
clients/python/text_generation/__init__.py	16
clients/python/text_generation/inference_api.py	55