Path	Lines of Code
backends/gaudi/server/text_generation_server/cli.py	297
backends/gaudi/server/text_generation_server/layers/attention/kv_cache.py	138
backends/gaudi/server/text_generation_server/layers/compressed_tensors/w8an_fp.py	209
backends/gaudi/server/text_generation_server/layers/fp8.py	528
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/lora.py	197
backends/gaudi/server/text_generation_server/models/__init__.py	984
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_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_gemma3_modeling.py	629
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_mistral_modeling.py	422
backends/gaudi/server/text_generation_server/models/custom_modeling/flash_pali_gemma_modeling.py	98
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/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/mllama_causal_lm.py	546
backends/gaudi/server/text_generation_server/models/model.py	111
backends/gaudi/server/text_generation_server/server.py	265
backends/gaudi/server/text_generation_server/utils/logits_process.py	402
backends/gaudi/server/text_generation_server/utils/quantization.py	137
backends/gaudi/server/text_generation_server/utils/tokens.py	634
backends/llamacpp/src/backend.rs	614
backends/trtllm/src/looper.rs	281
backends/v3/src/backend.rs	450
backends/v3/src/radix.rs	741
launcher/src/main.rs	1815
router/src/server.rs	2105
router/src/validation.rs	1186
server/custom_kernels/custom_kernels/fused_attention_cuda.cu	219
server/custom_kernels/custom_kernels/fused_bloom_attention_cuda.cu	219
server/exllama_kernels/exllama_kernels/cuda_func/q4_matrix.cu	166
server/exllama_kernels/exllama_kernels/matrix.cuh	250
server/text_generation_server/cli.py	301
server/text_generation_server/layers/attention/cuda.py	284
server/text_generation_server/layers/attention/flash_attn_triton.py	649
server/text_generation_server/layers/compressed_tensors/w8an_fp.py	150
server/text_generation_server/layers/fp8.py	452
server/text_generation_server/layers/gptq/quantize.py	855
server/text_generation_server/layers/lora.py	201
server/text_generation_server/models/__init__.py	1742
server/text_generation_server/models/custom_modeling/bloom_modeling.py	652
server/text_generation_server/models/custom_modeling/clip.py	466
server/text_generation_server/models/custom_modeling/flash_deepseek_v2_modeling.py	561
server/text_generation_server/models/custom_modeling/flash_deepseek_v3_modeling.py	569
server/text_generation_server/models/custom_modeling/flash_gemma3_modeling.py	724
server/text_generation_server/models/custom_modeling/flash_llama_modeling.py	581
server/text_generation_server/models/custom_modeling/flash_mistral_modeling.py	457
server/text_generation_server/models/custom_modeling/flash_pali_gemma_modeling.py	101
server/text_generation_server/models/custom_modeling/gemma3/image_processing_gemma3.py	300
server/text_generation_server/models/custom_modeling/idefics_image_processing.py	145
server/text_generation_server/models/custom_modeling/mpt_modeling.py	1105
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/vlm.py	55
server/text_generation_server/models/flash_causal_lm.py	2009
server/text_generation_server/models/idefics_causal_lm.py	708
server/text_generation_server/models/mamba.py	667
server/text_generation_server/models/metadata_kernels.py	250
server/text_generation_server/models/mllama_causal_lm.py	330
server/text_generation_server/models/model.py	146
server/text_generation_server/models/transformers_flash_vlm.py	499
server/text_generation_server/models/vlm_causal_lm.py	931
server/text_generation_server/utils/logits_process.py	412
server/text_generation_server/utils/quantization.py	181
server/text_generation_server/utils/tokens.py	530