init

# Please enter the commit message for your changes. Lines starting
# with '#' will be ignored, and an empty message aborts the commit.
#
# Date:      Fri Nov 1 13:56:39 2024 +0800
#
# On branch main
# Changes to be committed:
#	new file:   .clang-format
#	new file:   .gitignore
#	new file:   .gitmodules
#	new file:   3rdparty/argparse
#	new file:   3rdparty/googletest
#	new file:   3rdparty/stb
#	new file:   3rdparty/tokenizers-cpp
#	new file:   3rdparty/tvm
#	new file:   CMakeLists.txt
#	new file:   README.md
#	new file:   android/.gitignore
#	new file:   android/TapMLChat/app/.gitignore
#	new file:   android/TapMLChat/app/build.gradle
#	new file:   android/TapMLChat/app/proguard-rules.pro
#	new file:   android/TapMLChat/app/src/main/AndroidManifest.xml
#	new file:   android/TapMLChat/app/src/main/ic_launcher-playstore.png
#	new file:   android/TapMLChat/app/src/main/java/ai/tapml/tapml/AppViewModel.kt
#	new file:   android/TapMLChat/app/src/main/java/ai/tapml/tapml/ChatView.kt
#	new file:   android/TapMLChat/app/src/main/java/ai/tapml/tapml/MainActivity.kt
#	new file:   android/TapMLChat/app/src/main/java/ai/tapml/tapml/NavView.kt
#	new file:   android/TapMLChat/app/src/main/java/ai/tapml/tapml/StartView.kt
#	new file:   android/TapMLChat/app/src/main/java/ai/tapml/tapml/ui/theme/Color.kt
#	new file:   android/TapMLChat/app/src/main/java/ai/tapml/tapml/ui/theme/Theme.kt
#	new file:   android/TapMLChat/app/src/main/java/ai/tapml/tapml/ui/theme/Type.kt
#	new file:   android/TapMLChat/app/src/main/res/drawable/ic_android_black_24dp.xml
#	new file:   android/TapMLChat/app/src/main/res/drawable/tapml_logo_108.xml
#	new file:   android/TapMLChat/app/src/main/res/values/colors.xml
#	new file:   android/TapMLChat/app/src/main/res/values/strings.xml
#	new file:   android/TapMLChat/app/src/main/res/values/themes.xml
#	new file:   android/TapMLChat/app/src/main/res/xml/backup_rules.xml
#	new file:   android/TapMLChat/app/src/main/res/xml/data_extraction_rules.xml
#	new file:   android/TapMLChat/build.gradle
#	new file:   android/TapMLChat/bundle_weight.py
#	new file:   android/TapMLChat/gradle.properties
#	new file:   android/TapMLChat/gradle/wrapper/gradle-wrapper.jar
#	new file:   android/TapMLChat/gradle/wrapper/gradle-wrapper.properties
#	new file:   android/TapMLChat/gradlew
#	new file:   android/TapMLChat/gradlew.bat
#	new file:   android/TapMLChat/settings.gradle
#	new file:   android/tapml4j/.gitignore
#	new file:   android/tapml4j/CMakeLists.txt
#	new file:   android/tapml4j/build.gradle
#	new file:   android/tapml4j/prepare_libs.py
#	new file:   android/tapml4j/src/cpp/tvm_runtime.h
#	new file:   android/tapml4j/src/main/AndroidManifest.xml
#	new file:   android/tapml4j/src/main/java/ai/tapml/tapml/JSONFFIEngine.java
#	new file:   android/tapml4j/src/main/java/ai/tapml/tapml/OpenAIProtocol.kt
#	new file:   android/tapml4j/src/main/java/ai/tapml/tapml/TapMLEngine.kt
#	new file:   cmake/gen_cmake_config.py
#	new file:   cpp/base.h
#	new file:   cpp/grammar/grammar.cc
#	new file:   cpp/grammar/grammar.h
#	new file:   cpp/grammar/grammar_builder.h
#	new file:   cpp/grammar/grammar_functor.cc
#	new file:   cpp/grammar/grammar_functor.h
#	new file:   cpp/grammar/grammar_parser.cc
#	new file:   cpp/grammar/grammar_parser.h
#	new file:   cpp/grammar/grammar_serializer.cc
#	new file:   cpp/grammar/grammar_serializer.h
#	new file:   cpp/grammar/grammar_state_matcher.cc
#	new file:   cpp/grammar/grammar_state_matcher.h
#	new file:   cpp/grammar/grammar_state_matcher_base.h
#	new file:   cpp/grammar/grammar_state_matcher_preproc.h
#	new file:   cpp/grammar/grammar_state_matcher_state.h
#	new file:   cpp/grammar/json_schema_converter.cc
#	new file:   cpp/grammar/json_schema_converter.h
#	new file:   cpp/grammar/support.h
#	new file:   cpp/json_ffi/conv_template.cc
#	new file:   cpp/json_ffi/conv_template.h
#	new file:   cpp/json_ffi/image_utils.cc
#	new file:   cpp/json_ffi/image_utils.h
#	new file:   cpp/json_ffi/json_ffi_engine.cc
#	new file:   cpp/json_ffi/json_ffi_engine.h
#	new file:   cpp/json_ffi/openai_api_protocol.cc
#	new file:   cpp/json_ffi/openai_api_protocol.h
#	new file:   cpp/metadata/model.cc
#	new file:   cpp/metadata/model.h
#	new file:   cpp/multi_gpu/builtin.cc
#	new file:   cpp/multi_gpu/multi_gpu_loader.cc
#	new file:   cpp/serve/config.cc
#	new file:   cpp/serve/config.h
#	new file:   cpp/serve/data.cc
#	new file:   cpp/serve/data.h
#	new file:   cpp/serve/draft_token_workspace_manager.cc
#	new file:   cpp/serve/draft_token_workspace_manager.h
#	new file:   cpp/serve/engine.cc
#	new file:   cpp/serve/engine.h
#	new file:   cpp/serve/engine_actions/action.cc
#	new file:   cpp/serve/engine_actions/action.h
#	new file:   cpp/serve/engine_actions/action_commons.cc
#	new file:   cpp/serve/engine_actions/action_commons.h
#	new file:   cpp/serve/engine_actions/auto_spec_decode.cc
#	new file:   cpp/serve/engine_actions/batch_decode.cc
#	new file:   cpp/serve/engine_actions/batch_draft.cc
#	new file:   cpp/serve/engine_actions/batch_jumpforward.cc
#	new file:   cpp/serve/engine_actions/batch_prefill_base.cc
#	new file:   cpp/serve/engine_actions/batch_prefill_base.h
#	new file:   cpp/serve/engine_actions/batch_verify.cc
#	new file:   cpp/serve/engine_actions/eagle_batch_draft.cc
#	new file:   cpp/serve/engine_actions/eagle_batch_verify.cc
#	new file:   cpp/serve/engine_actions/eagle_new_request_prefill.cc
#	new file:   cpp/serve/engine_actions/new_request_prefill.cc
#	new file:   cpp/serve/engine_state.cc
#	new file:   cpp/serve/engine_state.h
#	new file:   cpp/serve/event_trace_recorder.cc
#	new file:   cpp/serve/event_trace_recorder.h
#	new file:   cpp/serve/function_table.cc
#	new file:   cpp/serve/function_table.h
#	new file:   cpp/serve/logit_processor.cc
#	new file:   cpp/serve/logit_processor.h
#	new file:   cpp/serve/metrics.cc
#	new file:   cpp/serve/metrics.h
#	new file:   cpp/serve/model.cc
#	new file:   cpp/serve/model.h
#	new file:   cpp/serve/prefix_cache.cc
#	new file:   cpp/serve/prefix_cache.h
#	new file:   cpp/serve/radix_tree.cc
#	new file:   cpp/serve/radix_tree.h
#	new file:   cpp/serve/request.cc
#	new file:   cpp/serve/request.h
#	new file:   cpp/serve/request_state.cc
#	new file:   cpp/serve/request_state.h
#	new file:   cpp/serve/sampler/cpu_sampler.cc
#	new file:   cpp/serve/sampler/gpu_sampler.cc
#	new file:   cpp/serve/sampler/sampler.h
#	new file:   cpp/serve/threaded_engine.cc
#	new file:   cpp/serve/threaded_engine.h
#	new file:   cpp/support/debug_utils.h
#	new file:   cpp/support/dynamic_bitset.h
#	new file:   cpp/support/encoding.cc
#	new file:   cpp/support/encoding.h
#	new file:   cpp/support/json_parser.h
#	new file:   cpp/support/load_bytes_from_file.h
#	new file:   cpp/support/progress_bar.h
#	new file:   cpp/support/random.h
#	new file:   cpp/support/result.h
#	new file:   cpp/support/utils.h
#	new file:   cpp/tokenizers/streamer.cc
#	new file:   cpp/tokenizers/streamer.h
#	new file:   cpp/tokenizers/tokenizers.cc
#	new file:   cpp/tokenizers/tokenizers.h
#	new file:   eval/.gitignore
#	new file:   eval/cases/0/bottom-up.py
#	new file:   eval/cases/0/bottom-up.txt
#	new file:   eval/cases/0/golden_tir.py
#	new file:   eval/cases/0/opinfo.txt
#	new file:   eval/cases/0/top-down.txt
#	new file:   eval/cases/1/bottom-up.py
#	new file:   eval/cases/1/bottom-up.txt
#	new file:   eval/cases/1/golden_tir.py
#	new file:   eval/cases/1/opinfo.txt
#	new file:   eval/cases/1/top-down.txt
#	new file:   eval/cases/2/bottom-up.py
#	new file:   eval/cases/2/bottom-up.txt
#	new file:   eval/cases/2/golden_tir.py
#	new file:   eval/cases/2/opinfo.txt
#	new file:   eval/cases/2/top-down.txt
#	new file:   eval/cases/3/bottom-up.py
#	new file:   eval/cases/3/bottom-up.txt
#	new file:   eval/cases/3/golden_tir.py
#	new file:   eval/cases/3/opinfo.txt
#	new file:   eval/cases/3/top-down.txt
#	new file:   eval/cases/4/bottom-up.py
#	new file:   eval/cases/4/bottom-up.txt
#	new file:   eval/cases/4/golden_tir.py
#	new file:   eval/cases/4/opinfo.txt
#	new file:   eval/cases/4/top-down.txt
#	new file:   eval/cases/5/bottom-up.py
#	new file:   eval/cases/5/bottom-up.txt
#	new file:   eval/cases/5/golden_tir.py
#	new file:   eval/cases/5/opinfo.txt
#	new file:   eval/cases/5/top-down.txt
#	new file:   eval/cases/6/bottom-up.py
#	new file:   eval/cases/6/bottom-up.txt
#	new file:   eval/cases/6/golden_tir.py
#	new file:   eval/cases/6/opinfo.txt
#	new file:   eval/cases/6/top-down.txt
#	new file:   eval/cases/7/bottom-up.py
#	new file:   eval/cases/7/bottom-up.txt
#	new file:   eval/cases/7/golden_tir.py
#	new file:   eval/cases/7/opinfo.txt
#	new file:   eval/cases/7/top-down.txt
#	new file:   eval/cases/8/bottom-up.py
#	new file:   eval/cases/8/bottom-up.txt
#	new file:   eval/cases/8/golden_tir.py
#	new file:   eval/cases/8/opinfo.txt
#	new file:   eval/cases/8/top-down.txt
#	new file:   eval/cases/9/bottom-up.py
#	new file:   eval/cases/9/bottom-up.txt
#	new file:   eval/cases/9/golden_tir.py
#	new file:   eval/cases/9/opinfo.txt
#	new file:   eval/cases/9/top-down.txt
#	new file:   eval/ground_truth/0.txt
#	new file:   eval/ground_truth/1.txt
#	new file:   eval/ground_truth/2.txt
#	new file:   eval/ground_truth/3.txt
#	new file:   eval/ground_truth/4.txt
#	new file:   eval/ground_truth/5.txt
#	new file:   eval/ground_truth/6.txt
#	new file:   eval/ground_truth/7.txt
#	new file:   eval/ground_truth/8.txt
#	new file:   eval/ground_truth/9.txt
#	new file:   eval/script/build_buggy.sh
#	new file:   eval/script/build_golden.sh
#	new file:   eval/script/get_function.py
#	new file:   eval/script/model_list.txt
#	new file:   eval/script/top-down.py
#	new file:   ios/.gitignore
#	new file:   ios/TapMLChat/TapMLChat.xcodeproj/project.pbxproj
#	new file:   ios/TapMLChat/TapMLChat.xcodeproj/project.xcworkspace/contents.xcworkspacedata
#	new file:   ios/TapMLChat/TapMLChat.xcodeproj/project.xcworkspace/xcshareddata/IDEWorkspaceChecks.plist
#	new file:   ios/TapMLChat/TapMLChat.xcodeproj/project.xcworkspace/xcshareddata/WorkspaceSettings.xcsettings
#	new file:   ios/TapMLChat/TapMLChat.xcodeproj/xcshareddata/xcschemes/TapMLChat.xcscheme
#	new file:   ios/TapMLChat/TapMLChat/Assets.xcassets/AccentColor.colorset/Contents.json
#	new file:   ios/TapMLChat/TapMLChat/Assets.xcassets/AppIcon.appiconset/Contents.json
#	new file:   ios/TapMLChat/TapMLChat/Assets.xcassets/AppIcon.appiconset/tapml-logo.png
#	new file:   ios/TapMLChat/TapMLChat/Assets.xcassets/Contents.json
#	new file:   ios/TapMLChat/TapMLChat/Common/Constants.swift
#	new file:   ios/TapMLChat/TapMLChat/Info.plist
#	new file:   ios/TapMLChat/TapMLChat/Models/AppConfig.swift
#	new file:   ios/TapMLChat/TapMLChat/Models/ModelConfig.swift
#	new file:   ios/TapMLChat/TapMLChat/Models/ParamsConfig.swift
#	new file:   ios/TapMLChat/TapMLChat/Preview Content/Preview Assets.xcassets/Contents.json
#	new file:   ios/TapMLChat/TapMLChat/States/AppState.swift
#	new file:   ios/TapMLChat/TapMLChat/States/ChatState.swift
#	new file:   ios/TapMLChat/TapMLChat/States/ModelState.swift
#	new file:   ios/TapMLChat/TapMLChat/TapMLChat.entitlements
#	new file:   ios/TapMLChat/TapMLChat/TapMLChatApp.swift
#	new file:   ios/TapMLChat/TapMLChat/Views/ChatView.swift
#	new file:   ios/TapMLChat/TapMLChat/Views/ImageProcessing.swift
#	new file:   ios/TapMLChat/TapMLChat/Views/MessageView.swift
#	new file:   ios/TapMLChat/TapMLChat/Views/ModelView.swift
#	new file:   ios/TapMLChat/TapMLChat/Views/StartView.swift
#	new file:   ios/TapMLSwift/Package.swift
#	new file:   ios/TapMLSwift/Sources/ObjC/LLMEngine.mm
#	new file:   ios/TapMLSwift/Sources/ObjC/include/LLMEngine.h
#	new file:   ios/TapMLSwift/Sources/Swift/LLMEngine.swift
#	new file:   ios/TapMLSwift/Sources/Swift/OpenAIProtocol.swift
#	new file:   ios/prepare_libs.sh
#	new file:   pyproject.toml
#	new file:   python/setup.py
#	new file:   python/tapml/__init__.py
#	new file:   python/tapml/__main__.py
#	new file:   python/tapml/base.py
#	new file:   python/tapml/bench/__init__.py
#	new file:   python/tapml/bench/__main__.py
#	new file:   python/tapml/bench/api_endpoint.py
#	new file:   python/tapml/bench/dataset.py
#	new file:   python/tapml/bench/request_processor.py
#	new file:   python/tapml/bench/request_record.py
#	new file:   python/tapml/cli/__init__.py
#	new file:   python/tapml/cli/calibrate.py
#	new file:   python/tapml/cli/chat.py
#	new file:   python/tapml/cli/check_device.py
#	new file:   python/tapml/cli/compile.py
#	new file:   python/tapml/cli/convert_weight.py
#	new file:   python/tapml/cli/delivery.py
#	new file:   python/tapml/cli/disco_remote_socket_session.py
#	new file:   python/tapml/cli/gen_config.py
#	new file:   python/tapml/cli/lib_delivery.py
#	new file:   python/tapml/cli/model_metadata.py
#	new file:   python/tapml/cli/package.py
#	new file:   python/tapml/cli/serve.py
#	new file:   python/tapml/cli/worker.py
#	new file:   python/tapml/compiler_pass/__init__.py
#	new file:   python/tapml/compiler_pass/attach_embedding_allocator.py
#	new file:   python/tapml/compiler_pass/attach_logit_processor.py
#	new file:   python/tapml/compiler_pass/attach_sampler.py
#	new file:   python/tapml/compiler_pass/attach_softmax_with_temperature.py
#	new file:   python/tapml/compiler_pass/attach_spec_decode_aux_funcs.py
#	new file:   python/tapml/compiler_pass/attach_support_info.py
#	new file:   python/tapml/compiler_pass/blas_dispatch.py
#	new file:   python/tapml/compiler_pass/clean_up_tir_attrs.py
#	new file:   python/tapml/compiler_pass/dispatch_kv_cache_creation.py
#	new file:   python/tapml/compiler_pass/estimate_memory_usage.py
#	new file:   python/tapml/compiler_pass/fuse_add_norm.py
#	new file:   python/tapml/compiler_pass/fuse_dequantize_matmul_ewise.py
#	new file:   python/tapml/compiler_pass/fuse_dequantize_take.py
#	new file:   python/tapml/compiler_pass/fuse_dequantize_transpose.py
#	new file:   python/tapml/compiler_pass/fuse_ft_dequantize_matmul_epilogue.py
#	new file:   python/tapml/compiler_pass/fuse_transpose_matmul.py
#	new file:   python/tapml/compiler_pass/lift_global_buffer_alloc.py
#	new file:   python/tapml/compiler_pass/low_batch_specialization.py
#	new file:   python/tapml/compiler_pass/pipeline.py
#	new file:   python/tapml/compiler_pass/pipeline_parallel_rewrite.py
#	new file:   python/tapml/compiler_pass/scatter_tuple_get_item.py
#	new file:   python/tapml/contrib/__init__.py
#	new file:   python/tapml/contrib/embeddings/__init__.py
#	new file:   python/tapml/contrib/embeddings/embeddings.py
#	new file:   python/tapml/contrib/embeddings/openai.py
#	new file:   python/tapml/conversation_template/__init__.py
#	new file:   python/tapml/conversation_template/cohere.py
#	new file:   python/tapml/conversation_template/deepseek.py
#	new file:   python/tapml/conversation_template/deepseek_v2.py
#	new file:   python/tapml/conversation_template/dolly.py
#	new file:   python/tapml/conversation_template/gemma.py
#	new file:   python/tapml/conversation_template/glm.py
#	new file:   python/tapml/conversation_template/gorrilla.py
#	new file:   python/tapml/conversation_template/gpt.py
#	new file:   python/tapml/conversation_template/hermes.py
#	new file:   python/tapml/conversation_template/llama.py
#	new file:   python/tapml/conversation_template/llava.py
#	new file:   python/tapml/conversation_template/mistral.py
#	new file:   python/tapml/conversation_template/oasst.py
#	new file:   python/tapml/conversation_template/orion.py
#	new file:   python/tapml/conversation_template/phi.py
#	new file:   python/tapml/conversation_template/qwen2.py
#	new file:   python/tapml/conversation_template/redpajama.py
#	new file:   python/tapml/conversation_template/registry.py
#	new file:   python/tapml/conversation_template/rwkv.py
#	new file:   python/tapml/conversation_template/stablelm.py
#	new file:   python/tapml/conversation_template/tinyllama.py
#	new file:   python/tapml/conversation_template/wizardlm.py
#	new file:   python/tapml/grammar/__init__.py
#	new file:   python/tapml/grammar/_ffi_api.py
#	new file:   python/tapml/grammar/grammar.py
#	new file:   python/tapml/interface/__init__.py
#	new file:   python/tapml/interface/calibrate.py
#	new file:   python/tapml/interface/chat.py
#	new file:   python/tapml/interface/compile.py
#	new file:   python/tapml/interface/compiler_flags.py
#	new file:   python/tapml/interface/convert_weight.py
#	new file:   python/tapml/interface/gen_config.py
#	new file:   python/tapml/interface/help.py
#	new file:   python/tapml/interface/jit.py
#	new file:   python/tapml/interface/package.py
#	new file:   python/tapml/interface/serve.py
#	new file:   python/tapml/json_ffi/__init__.py
#	new file:   python/tapml/json_ffi/engine.py
#	new file:   python/tapml/libinfo.py
#	new file:   python/tapml/loader/__init__.py
#	new file:   python/tapml/loader/huggingface_loader.py
#	new file:   python/tapml/loader/loader.py
#	new file:   python/tapml/loader/mapping.py
#	new file:   python/tapml/loader/stats.py
#	new file:   python/tapml/loader/utils.py
#	new file:   python/tapml/model/__init__.py
#	new file:   python/tapml/model/baichuan/__init__.py
#	new file:   python/tapml/model/baichuan/baichuan_loader.py
#	new file:   python/tapml/model/baichuan/baichuan_model.py
#	new file:   python/tapml/model/baichuan/baichuan_quantization.py
#	new file:   python/tapml/model/bert/__init__.py
#	new file:   python/tapml/model/bert/bert_loader.py
#	new file:   python/tapml/model/bert/bert_model.py
#	new file:   python/tapml/model/bert/bert_quantization.py
#	new file:   python/tapml/model/chatglm3/__init__.py
#	new file:   python/tapml/model/chatglm3/chatglm3_loader.py
#	new file:   python/tapml/model/chatglm3/chatglm3_model.py
#	new file:   python/tapml/model/chatglm3/chatglm3_quantization.py
#	new file:   python/tapml/model/cohere/__init__.py
#	new file:   python/tapml/model/cohere/cohere_loader.py
#	new file:   python/tapml/model/cohere/cohere_model.py
#	new file:   python/tapml/model/cohere/cohere_quantization.py
#	new file:   python/tapml/model/deepseek/__init__.py
#	new file:   python/tapml/model/deepseek/deepseek_loader.py
#	new file:   python/tapml/model/deepseek/deepseek_model.py
#	new file:   python/tapml/model/deepseek/deepseek_quantization.py
#	new file:   python/tapml/model/deepseek_v2/__init__.py
#	new file:   python/tapml/model/deepseek_v2/deepseek_v2_loader.py
#	new file:   python/tapml/model/deepseek_v2/deepseek_v2_model.py
#	new file:   python/tapml/model/deepseek_v2/deepseek_v2_quantization.py
#	new file:   python/tapml/model/eagle/__init__.py
#	new file:   python/tapml/model/eagle/eagle_loader.py
#	new file:   python/tapml/model/eagle/eagle_model.py
#	new file:   python/tapml/model/eagle/eagle_quantization.py
#	new file:   python/tapml/model/gemma/__init__.py
#	new file:   python/tapml/model/gemma/gemma_loader.py
#	new file:   python/tapml/model/gemma/gemma_model.py
#	new file:   python/tapml/model/gemma/gemma_quantization.py
#	new file:   python/tapml/model/gemma2/__init__.py
#	new file:   python/tapml/model/gemma2/gemma2_loader.py
#	new file:   python/tapml/model/gemma2/gemma2_model.py
#	new file:   python/tapml/model/gemma2/gemma2_quantization.py
#	new file:   python/tapml/model/gpt2/__init__.py
#	new file:   python/tapml/model/gpt2/gpt2_loader.py
#	new file:   python/tapml/model/gpt2/gpt2_model.py
#	new file:   python/tapml/model/gpt2/gpt2_quantization.py
#	new file:   python/tapml/model/gpt_bigcode/__init__.py
#	new file:   python/tapml/model/gpt_bigcode/gpt_bigcode_loader.py
#	new file:   python/tapml/model/gpt_bigcode/gpt_bigcode_model.py
#	new file:   python/tapml/model/gpt_bigcode/gpt_bigcode_quantization.py
#	new file:   python/tapml/model/gpt_neox/__init__.py
#	new file:   python/tapml/model/gpt_neox/gpt_neox_loader.py
#	new file:   python/tapml/model/gpt_neox/gpt_neox_model.py
#	new file:   python/tapml/model/gpt_neox/gpt_neox_quantization.py
#	new file:   python/tapml/model/internlm/__init__.py
#	new file:   python/tapml/model/internlm/internlm_loader.py
#	new file:   python/tapml/model/internlm/internlm_model.py
#	new file:   python/tapml/model/internlm/internlm_quantization.py
#	new file:   python/tapml/model/internlm2/__init__.py
#	new file:   python/tapml/model/internlm2/internlm2_loader.py
#	new file:   python/tapml/model/internlm2/internlm2_model.py
#	new file:   python/tapml/model/internlm2/internlm2_quantization.py
#	new file:   python/tapml/model/llama/__init__.py
#	new file:   python/tapml/model/llama/llama_loader.py
#	new file:   python/tapml/model/llama/llama_model.py
#	new file:   python/tapml/model/llama/llama_quantization.py
#	new file:   python/tapml/model/llava/__init__.py
#	new file:   python/tapml/model/llava/llava_loader.py
#	new file:   python/tapml/model/llava/llava_model.py
#	new file:   python/tapml/model/llava/llava_quantization.py
#	new file:   python/tapml/model/medusa/__init__.py
#	new file:   python/tapml/model/medusa/medusa_loader.py
#	new file:   python/tapml/model/medusa/medusa_model.py
#	new file:   python/tapml/model/medusa/medusa_quantization.py
#	new file:   python/tapml/model/minicpm/__init__.py
#	new file:   python/tapml/model/minicpm/minicpm_loader.py
#	new file:   python/tapml/model/minicpm/minicpm_model.py
#	new file:   python/tapml/model/minicpm/minicpm_quantization.py
#	new file:   python/tapml/model/mistral/__init__.py
#	new file:   python/tapml/model/mistral/mistral_loader.py
#	new file:   python/tapml/model/mistral/mistral_model.py
#	new file:   python/tapml/model/mistral/mistral_quantization.py
#	new file:   python/tapml/model/mixtral/__init__.py
#	new file:   python/tapml/model/mixtral/mixtral_loader.py
#	new file:   python/tapml/model/mixtral/mixtral_model.py
#	new file:   python/tapml/model/mixtral/mixtral_quantization.py
#	new file:   python/tapml/model/model.py
#	new file:   python/tapml/model/model_preset.py
#	new file:   python/tapml/model/orion/__init__.py
#	new file:   python/tapml/model/orion/orion_loader.py
#	new file:   python/tapml/model/orion/orion_model.py
#	new file:   python/tapml/model/orion/orion_quantization.py
#	new file:   python/tapml/model/phi/__init__.py
#	new file:   python/tapml/model/phi/phi_loader.py
#	new file:   python/tapml/model/phi/phi_model.py
#	new file:   python/tapml/model/phi/phi_quantization.py
#	new file:   python/tapml/model/phi3/__init__.py
#	new file:   python/tapml/model/phi3/phi3_loader.py
#	new file:   python/tapml/model/phi3/phi3_model.py
#	new file:   python/tapml/model/phi3/phi3_quantization.py
#	new file:   python/tapml/model/phi3v/__init__.py
#	new file:   python/tapml/model/phi3v/phi3v_image.py
#	new file:   python/tapml/model/phi3v/phi3v_loader.py
#	new file:   python/tapml/model/phi3v/phi3v_model.py
#	new file:   python/tapml/model/phi3v/phi3v_quantization.py
#	new file:   python/tapml/model/qwen/__init__.py
#	new file:   python/tapml/model/qwen/qwen_loader.py
#	new file:   python/tapml/model/qwen/qwen_model.py
#	new file:   python/tapml/model/qwen/qwen_quantization.py
#	new file:   python/tapml/model/qwen2/__init__.py
#	new file:   python/tapml/model/qwen2/qwen2_loader.py
#	new file:   python/tapml/model/qwen2/qwen2_model.py
#	new file:   python/tapml/model/qwen2/qwen2_quantization.py
#	new file:   python/tapml/model/qwen2_moe/__init__.py
#	new file:   python/tapml/model/qwen2_moe/qwen2_moe_loader.py
#	new file:   python/tapml/model/qwen2_moe/qwen2_moe_model.py
#	new file:   python/tapml/model/qwen2_moe/qwen2_moe_quantization.py
#	new file:   python/tapml/model/rwkv5/__init__.py
#	new file:   python/tapml/model/rwkv5/rwkv5_loader.py
#	new file:   python/tapml/model/rwkv5/rwkv5_model.py
#	new file:   python/tapml/model/rwkv5/rwkv5_quantization.py
#	new file:   python/tapml/model/rwkv6/__init__.py
#	new file:   python/tapml/model/rwkv6/rwkv6_loader.py
#	new file:   python/tapml/model/rwkv6/rwkv6_model.py
#	new file:   python/tapml/model/rwkv6/rwkv6_quantization.py
#	new file:   python/tapml/model/stable_lm/__init__.py
#	new file:   python/tapml/model/stable_lm/stablelm_loader.py
#	new file:   python/tapml/model/stable_lm/stablelm_model.py
#	new file:   python/tapml/model/stable_lm/stablelm_quantization.py
#	new file:   python/tapml/model/starcoder2/__init__.py
#	new file:   python/tapml/model/starcoder2/starcoder2_loader.py
#	new file:   python/tapml/model/starcoder2/starcoder2_model.py
#	new file:   python/tapml/model/starcoder2/starcoder2_quantization.py
#	new file:   python/tapml/model/vision/__init__.py
#	new file:   python/tapml/model/vision/clip_vision.py
#	new file:   python/tapml/model/vision/image_processing.py
#	new file:   python/tapml/nn/__init__.py
#	new file:   python/tapml/nn/expert.py
#	new file:   python/tapml/nn/kv_cache.py
#	new file:   python/tapml/nn/rnn_state.py
#	new file:   python/tapml/op/__init__.py
#	new file:   python/tapml/op/attention.py
#	new file:   python/tapml/op/batch_spec_verify.py
#	new file:   python/tapml/op/cutlass.py
#	new file:   python/tapml/op/extern.py
#	new file:   python/tapml/op/ft_gemm.py
#	new file:   python/tapml/op/moe_matmul.py
#	new file:   python/tapml/op/moe_misc.py
#	new file:   python/tapml/op/pipeline_parallel.py
#	new file:   python/tapml/op/position_embedding.py
#	new file:   python/tapml/op/top_p_pivot.py
#	new file:   python/tapml/protocol/__init__.py
#	new file:   python/tapml/protocol/conversation_protocol.py
#	new file:   python/tapml/protocol/debug_protocol.py
#	new file:   python/tapml/protocol/error_protocol.py
#	new file:   python/tapml/protocol/generation_config.py
#	new file:   python/tapml/protocol/openai_api_protocol.py
#	new file:   python/tapml/protocol/tapml_chat_config.py
#	new file:   python/tapml/quantization/__init__.py
#	new file:   python/tapml/quantization/awq_quantization.py
#	new file:   python/tapml/quantization/fp8_quantization.py
#	new file:   python/tapml/quantization/ft_quantization.py
#	new file:   python/tapml/quantization/group_quantization.py
#	new file:   python/tapml/quantization/no_quantization.py
#	new file:   python/tapml/quantization/per_tensor_quantization.py
#	new file:   python/tapml/quantization/quantization.py
#	new file:   python/tapml/quantization/utils.py
#	new file:   python/tapml/serve/__init__.py
#	new file:   python/tapml/serve/_ffi_api.py
#	new file:   python/tapml/serve/config.py
#	new file:   python/tapml/serve/data.py
#	new file:   python/tapml/serve/engine.py
#	new file:   python/tapml/serve/engine_base.py
#	new file:   python/tapml/serve/engine_utils.py
#	new file:   python/tapml/serve/entrypoints/__init__.py
#	new file:   python/tapml/serve/entrypoints/debug_entrypoints.py
#	new file:   python/tapml/serve/entrypoints/metrics_entrypoints.py
#	new file:   python/tapml/serve/entrypoints/openai_entrypoints.py
#	new file:   python/tapml/serve/event_trace_recorder.py
#	new file:   python/tapml/serve/radix_tree.py
#	new file:   python/tapml/serve/request.py
#	new file:   python/tapml/serve/server/__init__.py
#	new file:   python/tapml/serve/server/popen_server.py
#	new file:   python/tapml/serve/server/server_context.py
#	new file:   python/tapml/serve/sync_engine.py
#	new file:   python/tapml/support/__init__.py
#	new file:   python/tapml/support/argparse.py
#	new file:   python/tapml/support/auto_config.py
#	new file:   python/tapml/support/auto_device.py
#	new file:   python/tapml/support/auto_target.py
#	new file:   python/tapml/support/auto_weight.py
#	new file:   python/tapml/support/config.py
#	new file:   python/tapml/support/constants.py
#	new file:   python/tapml/support/convert_tiktoken.py
#	new file:   python/tapml/support/download_cache.py
#	new file:   python/tapml/support/logging.py
#	new file:   python/tapml/support/max_thread_check.py
#	new file:   python/tapml/support/preshard.py
#	new file:   python/tapml/support/random.py
#	new file:   python/tapml/support/style.py
#	new file:   python/tapml/support/tensor_parallel.py
#	new file:   python/tapml/support/tqdm.py
#	new file:   python/tapml/testing/__init__.py
#	new file:   python/tapml/testing/debug_chat.py
#	new file:   python/tapml/testing/debug_compare.py
#	new file:   python/tapml/testing/pytest_utils.py
#	new file:   python/tapml/tokenizers/__init__.py
#	new file:   python/tapml/tokenizers/_ffi_api.py
#	new file:   python/tapml/tokenizers/streamer.py
#	new file:   python/tapml/tokenizers/tokenizers.py
#	new file:   version.py
#
