LICENSE
MANIFEST.in
NOTICE
README.md
pyproject.toml
docs/API.md
docs/ARCHITECTURE.md
docs/EXPORT.md
docs/METRICS.md
docs/MODELS.md
docs/PLATFORMS.md
edgeserve/__init__.py
edgeserve/__main__.py
edgeserve/batch.py
edgeserve/check.py
edgeserve/cli.py
edgeserve/config.py
edgeserve/engine.py
edgeserve/exporter.py
edgeserve/hardware.py
edgeserve/keys.py
edgeserve/metrics.py
edgeserve/model.py
edgeserve/nativebuild.py
edgeserve/records.py
edgeserve/scheduler.py
edgeserve/service.py
edgeserve/settings.py
edgeserve/setupcmd.py
edgeserve/systemd.py
edgeserve/telemetry.py
edgeserve/tls.py
edgeserve/worker.py
edgeserve.egg-info/PKG-INFO
edgeserve.egg-info/SOURCES.txt
edgeserve.egg-info/dependency_links.txt
edgeserve.egg-info/entry_points.txt
edgeserve.egg-info/requires.txt
edgeserve.egg-info/top_level.txt
edgeserve/api/__init__.py
edgeserve/api/app.py
edgeserve/api/errors.py
edgeserve/api/protocol.py
edgeserve/export_patches/0001-per-layer-mlp-widths.patch
edgeserve/export_patches/0002-exact-int4-zero-points.patch
edgeserve/native/CMakeLists.txt
edgeserve/native/attention_check.cpp
edgeserve/native/build.sh
edgeserve/native/worker.cpp
edgeserve/native/edgellm/COMMIT
edgeserve/native/edgellm/patches/0001-nvrtc-include-path-for-cuda-before-12.9.patch
edgeserve/native/edgellm/patches/0002-cudaLibrary-compat-for-rmsnorm-layernorm-f16moe.patch
edgeserve/native/edgellm/patches/0003-propagate-cudaLaunchKernelEx-wrap-from-static-libs.patch
edgeserve/native/edgellm/patches/0004-optional-external-subdirectory.patch
edgeserve/native/edgellm/patches/0005-tolerate-missing-opt-profile-in-plugins.patch
tests/conftest.py
tests/fake_llm_build.py
tests/fake_worker.py
tests/test_access_and_limits.py
tests/test_batch.py
tests/test_build_script.py
tests/test_check.py
tests/test_config.py
tests/test_docs.py
tests/test_engine.py
tests/test_exporter.py
tests/test_hardware.py
tests/test_http_server.py
tests/test_metrics.py
tests/test_model.py
tests/test_native_worker.py
tests/test_nativebuild.py
tests/test_packaging.py
tests/test_protocol.py
tests/test_records.py
tests/test_scheduler.py
tests/test_service_api.py
tests/test_settings_cli.py
tests/test_setup.py
tests/test_systemd.py
tests/test_telemetry.py
tests/test_worker_client.py
tests/worker_mock/include/NvInferRuntime.h
tests/worker_mock/include/NvInferVersion.h
tests/worker_mock/include/cuda_runtime.h
tests/worker_mock/include/common/logger.h
tests/worker_mock/include/common/trtUtils.h
tests/worker_mock/include/common/version.h
tests/worker_mock/include/profiling/metrics.h
tests/worker_mock/include/profiling/timer.h
tests/worker_mock/include/runtime/llmInferenceRuntime.h
tests/worker_mock/include/runtime/llmRuntimeUtils.h
tests/worker_mock/include/runtime/streaming.h
tests/worker_mock/include/tokenizer/tokenizer.h