.gitignore
CMakeLists.txt
LICENSE
README.en.md
README.md
requirements.txt
setup.py
./sysHAX_adapter/__init__.py
./sysHAX_adapter/entrypoints/__init__.py
./sysHAX_adapter/entrypoints/__main__.py
./sysHAX_adapter/utils/__init__.py
./sysHAX_adapter/utils/logger.py
./sysHAX_adapter/vllm_adapter/__init__.py
./sysHAX_adapter/vllm_adapter/sampling_params.py
./sysHAX_adapter/vllm_adapter/sequence.py
./sysHAX_adapter/vllm_adapter/entrypoints/__init__.py
./sysHAX_adapter/vllm_adapter/entrypoints/openai/__init__.py
./sysHAX_adapter/vllm_adapter/entrypoints/openai/api_server.py
./sysHAX_adapter/vllm_adapter/entrypoints/openai/protocol.py
./sysHAX_adapter/vllm_adapter/executor/__init__.py
./sysHAX_adapter/vllm_adapter/executor/uniproc_executor.py
./sysHAX_adapter/vllm_adapter/model_executor/__init__.py
./sysHAX_adapter/vllm_adapter/model_executor/model_map.py
./sysHAX_adapter/vllm_adapter/model_executor/qwen2.py
./sysHAX_adapter/vllm_adapter/model_executor/qwen3_moe_af_separate.py
./sysHAX_adapter/vllm_adapter/model_loader/__init__.py
./sysHAX_adapter/vllm_adapter/model_loader/syshax_loader.py
./sysHAX_adapter/vllm_adapter/syshax/__init__.py
./sysHAX_adapter/vllm_adapter/syshax/shared_memory_manager.py
./sysHAX_adapter/vllm_adapter/syshax/syshax_config.py
./sysHAX_adapter/vllm_adapter/v1/__init__.py
./sysHAX_adapter/vllm_adapter/v1/core/__init__.py
./sysHAX_adapter/vllm_adapter/v1/core/sched/__init__.py
./sysHAX_adapter/vllm_adapter/v1/core/sched/scheduler.py
./sysHAX_adapter/vllm_adapter/v1/engine/__init__.py
./sysHAX_adapter/vllm_adapter/v1/engine/async_llm.py
./sysHAX_adapter/vllm_adapter/v1/engine/core.py
./sysHAX_adapter/vllm_adapter/v1/engine/core_client.py
./sysHAX_adapter/vllm_adapter/v1/engine/processor.py
./sysHAX_adapter/vllm_adapter/v1/executor/__init__.py
./sysHAX_adapter/vllm_adapter/v1/executor/executor.py
./sysHAX_adapter/vllm_adapter/v1/executor/multiproc_executor.py
./sysHAX_adapter/vllm_adapter/v1/executor/uniproc_executor.py
./sysHAX_adapter/vllm_adapter/v1/worker/__init__.py
./sysHAX_adapter/vllm_adapter/v1/worker/cpu_model_runner.py
./sysHAX_adapter/vllm_adapter/v1/worker/cpu_worker.py
./sysHAX_adapter/vllm_adapter/v1/worker/gpu_model_runner.py
./sysHAX_adapter/vllm_adapter/v1/worker/gpu_worker.py
csrc/cpu.cmake
csrc/cpu/config.h
csrc/cpu/cpu_bindings.cpp
csrc/cpu/cpu_inference.cpp
csrc/cpu/cpu_inference.h
csrc/cpu/cpu_inference_manager.cpp
csrc/cpu/cpu_inference_manager.h
csrc/cpu/cpu_utils.cpp
csrc/cpu/cpu_utils.h
csrc/cpu/memory_manager.cpp
csrc/cpu/memory_manager.h
csrc/cpu/merge_silu.cpp
csrc/cpu/merge_silu.h
csrc/cpu/model.h
csrc/cpu/model_weight_base.cpp
csrc/cpu/model_weight_base.h
csrc/cpu/qwen3_moe.cpp
csrc/cpu/qwen3_moe.h
csrc/cpu/tensor.cpp
csrc/cpu/tensor.h
csrc/cpu/tp_method.h
csrc/cpu/utils.h
csrc/cpu/weight.h
csrc/cpu/matmul/matmul_base.h
csrc/cpu/matmul/matmul_fp16.cpp
csrc/cpu/matmul/matmul_fp16.h
csrc/cpu/matmul/matmul_q4q8.cpp
csrc/cpu/matmul/matmul_q4q8.h
csrc/cpu/matmul/matmul_q8.cpp
csrc/cpu/matmul/matmul_q8.h
csrc/cpu/quantization/quantization_base.h
csrc/cpu/quantization/quantization_fp16.cpp
csrc/cpu/quantization/quantization_fp16.h
csrc/cpu/quantization/quantization_q4_0.cpp
csrc/cpu/quantization/quantization_q4_0.h
csrc/cpu/quantization/quantization_q8_0.cpp
csrc/cpu/quantization/quantization_q8_0.h
sysHAX_adapter/__init__.py
sysHAX_adapter.egg-info/PKG-INFO
sysHAX_adapter.egg-info/SOURCES.txt
sysHAX_adapter.egg-info/dependency_links.txt
sysHAX_adapter.egg-info/entry_points.txt
sysHAX_adapter.egg-info/not-zip-safe
sysHAX_adapter.egg-info/top_level.txt
sysHAX_adapter/entrypoints/__init__.py
sysHAX_adapter/entrypoints/__main__.py
sysHAX_adapter/utils/__init__.py
sysHAX_adapter/utils/logger.py
sysHAX_adapter/vllm_adapter/__init__.py
sysHAX_adapter/vllm_adapter/sampling_params.py
sysHAX_adapter/vllm_adapter/sequence.py
sysHAX_adapter/vllm_adapter/entrypoints/__init__.py
sysHAX_adapter/vllm_adapter/entrypoints/openai/__init__.py
sysHAX_adapter/vllm_adapter/entrypoints/openai/api_server.py
sysHAX_adapter/vllm_adapter/entrypoints/openai/protocol.py
sysHAX_adapter/vllm_adapter/executor/__init__.py
sysHAX_adapter/vllm_adapter/executor/uniproc_executor.py
sysHAX_adapter/vllm_adapter/model_executor/__init__.py
sysHAX_adapter/vllm_adapter/model_executor/model_map.py
sysHAX_adapter/vllm_adapter/model_executor/qwen2.py
sysHAX_adapter/vllm_adapter/model_executor/qwen3_moe_af_separate.py
sysHAX_adapter/vllm_adapter/model_loader/__init__.py
sysHAX_adapter/vllm_adapter/model_loader/syshax_loader.py
sysHAX_adapter/vllm_adapter/syshax/__init__.py
sysHAX_adapter/vllm_adapter/syshax/shared_memory_manager.py
sysHAX_adapter/vllm_adapter/syshax/syshax_config.py
sysHAX_adapter/vllm_adapter/v1/__init__.py
sysHAX_adapter/vllm_adapter/v1/core/__init__.py
sysHAX_adapter/vllm_adapter/v1/core/sched/__init__.py
sysHAX_adapter/vllm_adapter/v1/core/sched/scheduler.py
sysHAX_adapter/vllm_adapter/v1/engine/__init__.py
sysHAX_adapter/vllm_adapter/v1/engine/async_llm.py
sysHAX_adapter/vllm_adapter/v1/engine/core.py
sysHAX_adapter/vllm_adapter/v1/engine/core_client.py
sysHAX_adapter/vllm_adapter/v1/engine/processor.py
sysHAX_adapter/vllm_adapter/v1/executor/__init__.py
sysHAX_adapter/vllm_adapter/v1/executor/executor.py
sysHAX_adapter/vllm_adapter/v1/executor/multiproc_executor.py
sysHAX_adapter/vllm_adapter/v1/executor/uniproc_executor.py
sysHAX_adapter/vllm_adapter/v1/worker/__init__.py
sysHAX_adapter/vllm_adapter/v1/worker/cpu_model_runner.py
sysHAX_adapter/vllm_adapter/v1/worker/cpu_worker.py
sysHAX_adapter/vllm_adapter/v1/worker/gpu_model_runner.py
sysHAX_adapter/vllm_adapter/v1/worker/gpu_worker.py
test/cpp/CMakeLists.txt
test/cpp/cpu/test_cpu_inference_manager.cpp
test/cpp/cpu/test_matmul.h
test/cpp/cpu/test_matmul_f16.cpp
test/cpp/cpu/test_matmul_q8.cpp
test/cpp/cpu/test_memory_manager.cpp
test/python/vllm_adapter/model_loader/test_syshax_loader.py