LICENSE
README.md
setup.py
multi_loras/__init__.py
multi_loras/__main__.py
multi_loras/__version__.py
multi_loras/dare.py
multi_loras/delta_weights.py
multi_loras/extract_lora.py
multi_loras/merge_models.py
multi_loras/merge_peft_adapters.py
multi_loras/merging_methods.py
multi_loras.egg-info/PKG-INFO
multi_loras.egg-info/SOURCES.txt
multi_loras.egg-info/dependency_links.txt
multi_loras.egg-info/requires.txt
multi_loras.egg-info/top_level.txt
multi_loras/slora/__init__.py
multi_loras/slora/install_slora_kernel.py
multi_loras/slora/io_struct.py
multi_loras/slora/sampling_params.py
multi_loras/slora/slora_server.py
multi_loras/slora/common/__init__.py
multi_loras/slora/common/build_utils.py
multi_loras/slora/common/gqa_mem_manager.py
multi_loras/slora/common/infer_utils.py
multi_loras/slora/common/int8kv_mem_manager.py
multi_loras/slora/common/mem_allocator.py
multi_loras/slora/common/mem_manager.py
multi_loras/slora/common/ppl_int8kv_mem_manager.py
multi_loras/slora/common/basemodel/__init__.py
multi_loras/slora/common/basemodel/basemodel.py
multi_loras/slora/common/basemodel/infer_struct.py
multi_loras/slora/common/basemodel/layer_infer/__init__.py
multi_loras/slora/common/basemodel/layer_infer/base_layer_infer.py
multi_loras/slora/common/basemodel/layer_infer/post_layer_infer.py
multi_loras/slora/common/basemodel/layer_infer/pre_layer_infer.py
multi_loras/slora/common/basemodel/layer_infer/transformer_layer_infer.py
multi_loras/slora/common/basemodel/layer_infer/template/__init__.py
multi_loras/slora/common/basemodel/layer_infer/template/post_layer_infer_template.py
multi_loras/slora/common/basemodel/layer_infer/template/pre_layer_infer_template.py
multi_loras/slora/common/basemodel/layer_infer/template/transformer_layer_infer_template.py
multi_loras/slora/common/basemodel/layer_weights/__init__.py
multi_loras/slora/common/basemodel/layer_weights/base_layer_weight.py
multi_loras/slora/common/basemodel/layer_weights/hf_load_utils.py
multi_loras/slora/common/basemodel/layer_weights/pre_and_post_layer_weight.py
multi_loras/slora/common/basemodel/layer_weights/transformer_layer_weight.py
multi_loras/slora/common/basemodel/triton_kernel/__init__.py
multi_loras/slora/common/basemodel/triton_kernel/apply_penalty.py
multi_loras/slora/common/basemodel/triton_kernel/dequantize_gemm_int4.py
multi_loras/slora/common/basemodel/triton_kernel/dequantize_gemm_int8.py
multi_loras/slora/common/basemodel/triton_kernel/destindex_copy_kv.py
multi_loras/slora/common/basemodel/triton_kernel/quantize_gemm_int8.py
multi_loras/slora/common/configs/__init__.py
multi_loras/slora/common/configs/config.py
multi_loras/slora/models/__init__.py
multi_loras/slora/models/llama/__init__.py
multi_loras/slora/models/llama/infer_struct.py
multi_loras/slora/models/llama/model.py
multi_loras/slora/models/llama/layer_infer/__init__.py
multi_loras/slora/models/llama/layer_infer/post_layer_infer.py
multi_loras/slora/models/llama/layer_infer/pre_layer_infer.py
multi_loras/slora/models/llama/layer_infer/transformer_layer_infer.py
multi_loras/slora/models/llama/layer_weights/__init__.py
multi_loras/slora/models/llama/layer_weights/pre_and_post_layer_weight.py
multi_loras/slora/models/llama/layer_weights/transformer_layer_weight.py
multi_loras/slora/models/llama/triton_kernel/__init__.py
multi_loras/slora/models/llama/triton_kernel/context_flashattention_nopad.py
multi_loras/slora/models/llama/triton_kernel/rmsnorm.py
multi_loras/slora/models/llama/triton_kernel/rotary_emb.py
multi_loras/slora/models/llama/triton_kernel/token_attention_nopad_att1.py
multi_loras/slora/models/llama/triton_kernel/token_attention_nopad_reduceV.py
multi_loras/slora/models/llama/triton_kernel/token_attention_nopad_softmax.py
multi_loras/slora/models/llama/triton_kernel/token_attention_softmax_and_reducev.py
multi_loras/slora/models/llama2/__init__.py
multi_loras/slora/models/llama2/model.py
multi_loras/slora/models/llama2/layer_infer/__init__.py
multi_loras/slora/models/llama2/layer_infer/transformer_layer_infer.py
multi_loras/slora/models/llama2/layer_weights/__init__.py
multi_loras/slora/models/llama2/layer_weights/transformer_layer_weight.py
multi_loras/slora/models/llama2/triton_kernel/__init__.py
multi_loras/slora/models/llama2/triton_kernel/context_flashattention_nopad.py
multi_loras/slora/models/llama2/triton_kernel/token_attention_nopad_att1.py
multi_loras/slora/models/llama2/triton_kernel/token_attention_nopad_reduceV.py
multi_loras/slora/models/llama2/triton_kernel/token_attention_nopad_softmax.py
multi_loras/slora/models/llama2/triton_kernel/token_attention_softmax_and_reducev.py
multi_loras/slora/router/__init__.py
multi_loras/slora/router/abort_req_queue.py
multi_loras/slora/router/cluster_req_queue.py
multi_loras/slora/router/input_params.py
multi_loras/slora/router/manager.py
multi_loras/slora/router/peft_req_queue.py
multi_loras/slora/router/pets_req_queue.py
multi_loras/slora/router/profiler.py
multi_loras/slora/router/req_queue.py
multi_loras/slora/router/stats.py
multi_loras/slora/router/model_infer/__init__.py
multi_loras/slora/router/model_infer/infer_adapter.py
multi_loras/slora/router/model_infer/infer_batch.py
multi_loras/slora/router/model_infer/model_rpc.py
multi_loras/slora/router/model_infer/naive_infer_adapter.py
multi_loras/slora/router/model_infer/post_process.py
multi_loras/slora/utils/__init__.py
multi_loras/slora/utils/infer_utils.py
multi_loras/slora/utils/metric.py
multi_loras/slora/utils/model_load.py
multi_loras/slora/utils/model_utils.py
multi_loras/slora/utils/net_utils.py