Path	Lines of Code
backends/client/Cargo.toml	20
backends/client/build.rs	29
backends/client/src/lib.rs	68
backends/client/src/v2/client.rs	208
backends/client/src/v2/mod.rs	11
backends/client/src/v2/sharded_client.rs	202
backends/client/src/v3/client.rs	247
backends/client/src/v3/mod.rs	11
backends/client/src/v3/sharded_client.rs	217
backends/gaudi/server/pyproject.toml	38
backends/gaudi/server/text_generation_server/__init__.py	1
backends/gaudi/server/text_generation_server/adapters/__init__.py	8
backends/gaudi/server/text_generation_server/adapters/config.py	19
backends/gaudi/server/text_generation_server/adapters/lora.py	370
backends/gaudi/server/text_generation_server/adapters/weights.py	101
backends/gaudi/server/text_generation_server/cache.py	24
backends/gaudi/server/text_generation_server/cli.py	297
backends/gaudi/server/text_generation_server/interceptor.py	35
backends/gaudi/server/text_generation_server/layers/__init__.py	32
backends/gaudi/server/text_generation_server/layers/attention/__init__.py	30
backends/gaudi/server/text_generation_server/layers/attention/common.py	71
backends/gaudi/server/text_generation_server/layers/attention/hpu.py	178
backends/gaudi/server/text_generation_server/layers/attention/kv_cache.py	138
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/bnb.py	93
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/conv.py	33
backends/gaudi/server/text_generation_server/layers/exl2.py	52
backends/gaudi/server/text_generation_server/layers/fp8.py	528
backends/gaudi/server/text_generation_server/layers/gptq/__init__.py	371
backends/gaudi/server/text_generation_server/layers/gptq/hpu.py	163
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/layernorm.py	45
backends/gaudi/server/text_generation_server/layers/linear.py	28
backends/gaudi/server/text_generation_server/layers/lora.py	197
backends/gaudi/server/text_generation_server/layers/medusa.py	144
backends/gaudi/server/text_generation_server/layers/mlp.py	214
backends/gaudi/server/text_generation_server/layers/moe/__init__.py	201
backends/gaudi/server/text_generation_server/layers/moe/fp8.py	240
backends/gaudi/server/text_generation_server/layers/moe/fused_moe.py	97
backends/gaudi/server/text_generation_server/layers/moe/unquantized.py	113
backends/gaudi/server/text_generation_server/layers/rotary.py	507
backends/gaudi/server/text_generation_server/layers/speculative.py	44
backends/gaudi/server/text_generation_server/layers/tensor_parallel.py	184
backends/gaudi/server/text_generation_server/models/__init__.py	984
backends/gaudi/server/text_generation_server/models/custom_modeling/__init__.py	1
backends/gaudi/server/text_generation_server/models/custom_modeling/bloom_modeling.py	652
backends/gaudi/server/text_generation_server/models/custom_modeling/clip.py	466
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_cohere_modeling.py	422
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_dbrx_modeling.py	614
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_deepseek_v3_modeling.py	604
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_gemma2_modeling.py	492
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_gemma3_modeling.py	629
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_gemma_modeling.py	401
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_gpt2_modeling.py	366
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_gptj_modeling.py	330
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_llama4_modeling.py	1116
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_llama_modeling.py	555
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_llava_next.py	201
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_mistral_modeling.py	422
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_mixtral_modeling.py	422
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_mllama.py	748
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_neox_modeling.py	344
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_phi_modeling.py	363
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_qwen2_modeling.py	333
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_qwen3_modeling.py	302
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_rw_modeling.py	578
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_santacoder_modeling.py	442
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_starcoder2_modeling.py	515
backends/gaudi/server/text_generation_server/models/custom_modeling/idefics2.py	677
backends/gaudi/server/text_generation_server/models/custom_modeling/idefics3.py	467
backends/gaudi/server/text_generation_server/models/custom_modeling/mamba_modeling.py	207
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/siglip.py	297
backends/gaudi/server/text_generation_server/models/custom_modeling/vlm.py	55
backends/gaudi/server/text_generation_server/models/flash_causal_lm.py	2113
backends/gaudi/server/text_generation_server/models/flash_vlm_causal_lm.py	856
backends/gaudi/server/text_generation_server/models/globals.py	33
backends/gaudi/server/text_generation_server/models/mllama_causal_lm.py	546
backends/gaudi/server/text_generation_server/models/model.py	111
backends/gaudi/server/text_generation_server/models/seq2seq_lm.py	737
backends/gaudi/server/text_generation_server/models/types.py	82
backends/gaudi/server/text_generation_server/server.py	265
backends/gaudi/server/text_generation_server/tgi_service.py	46
backends/gaudi/server/text_generation_server/tracing.py	44
backends/gaudi/server/text_generation_server/utils/__init__.py	47
backends/gaudi/server/text_generation_server/utils/adapter.py	243
backends/gaudi/server/text_generation_server/utils/chunks.py	17
backends/gaudi/server/text_generation_server/utils/convert.py	82
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/hub.py	174
backends/gaudi/server/text_generation_server/utils/import_utils.py	11
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/logits_process.py	402
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/peft.py	59
backends/gaudi/server/text_generation_server/utils/prefill_chunking.py	15
backends/gaudi/server/text_generation_server/utils/quantization.py	137
backends/gaudi/server/text_generation_server/utils/segments.py	38
backends/gaudi/server/text_generation_server/utils/sgmv.py	159
backends/gaudi/server/text_generation_server/utils/speculate.py	7
backends/gaudi/server/text_generation_server/utils/tokens.py	634
backends/gaudi/server/text_generation_server/utils/version.py	27
backends/gaudi/server/text_generation_server/utils/watermark.py	70
backends/gaudi/server/text_generation_server/utils/weights.py	295
backends/grpc-metadata/Cargo.toml	9
backends/grpc-metadata/src/lib.rs	32
backends/llamacpp/Cargo.toml	20
backends/llamacpp/build.rs	43
backends/llamacpp/src/backend.rs	614
backends/llamacpp/src/llamacpp.rs	5
backends/llamacpp/src/main.rs	266
backends/llamacpp/src/quantize.rs	30
backends/neuron/Cargo.toml	42
backends/neuron/server/pyproject.toml	23
backends/neuron/server/text_generation_server/cli.py	69
backends/neuron/server/text_generation_server/generator.py	501
backends/neuron/server/text_generation_server/interceptor.py	25
backends/neuron/server/text_generation_server/model.py	99
backends/neuron/server/text_generation_server/server.py	69
backends/neuron/server/text_generation_server/tgi_env.py	229
backends/neuron/tgi_entry_point.py	34
backends/trtllm/Cargo.toml	23
backends/trtllm/build.rs	203
backends/trtllm/cmake/json.cmake	6
backends/trtllm/cmake/spdlog.cmake	15
backends/trtllm/cmake/trtllm.cmake	40
backends/trtllm/cmake/utils/detect_cuda_arch.cu	1
backends/trtllm/csrc/backend.cpp	59
backends/trtllm/csrc/backend.hpp	133
backends/trtllm/csrc/ffi.hpp	156
backends/trtllm/csrc/hardware.hpp	38
backends/trtllm/scripts/setup_sccache.py	37
backends/trtllm/src/errors.rs	20
backends/trtllm/src/lib.rs	67
backends/trtllm/src/looper.rs	281
backends/trtllm/src/main.rs	296
backends/trtllm/src/utils.rs	4
backends/v2/Cargo.toml	70
backends/v2/build.rs	15
backends/v2/src/backend.rs	402
backends/v2/src/client/grpc_client.rs	208
backends/v2/src/client/mod.rs	52
backends/v2/src/client/sharded_client.rs	203
backends/v2/src/lib.rs	118
backends/v2/src/main.rs	203
backends/v2/src/queue.rs	527
backends/v3/Cargo.toml	77
backends/v3/benches/prefix_cache.rs	29
backends/v3/build.rs	15
backends/v3/src/backend.rs	450
backends/v3/src/block_allocator.rs	193
backends/v3/src/client/grpc_client.rs	255
backends/v3/src/client/mod.rs	50
backends/v3/src/client/sharded_client.rs	207
backends/v3/src/lib.rs	159
backends/v3/src/main.rs	217
backends/v3/src/queue.rs	670
backends/v3/src/radix.rs	741