LICENSE
MANIFEST.in
README.md
pyproject.toml
setup.py
arctic_inference/__init__.py
arctic_inference/patching.py
arctic_inference/py_custom_ops.py
arctic_inference/utils.py
arctic_inference.egg-info/PKG-INFO
arctic_inference.egg-info/SOURCES.txt
arctic_inference.egg-info/dependency_links.txt
arctic_inference.egg-info/entry_points.txt
arctic_inference.egg-info/requires.txt
arctic_inference.egg-info/top_level.txt
arctic_inference/common/__init__.py
arctic_inference/common/suffix_cache/__init__.py
arctic_inference/common/suffix_cache/simulator.py
arctic_inference/common/suffix_cache/suffix_cache.py
arctic_inference/common/swiftkv/__init__.py
arctic_inference/common/swiftkv/configs.py
arctic_inference/dynasor/__init__.py
arctic_inference/dynasor/cot.py
arctic_inference/dynasor/entropy.py
arctic_inference/dynasor/evaluator.py
arctic_inference/dynasor/openai_server.py
arctic_inference/dynasor/util.py
arctic_inference/dynasor/vllm_server.py
arctic_inference/embedding/client.py
arctic_inference/embedding/generate_proto.py
arctic_inference/embedding/replica.py
arctic_inference/embedding/replica_manager.py
arctic_inference/embedding/proto/inference.proto
arctic_inference/vllm/__init__.py
arctic_inference/vllm/args.py
arctic_inference/vllm/config.py
arctic_inference/vllm/model_runner.py
arctic_inference/vllm/plugins.py
arctic_inference/vllm/shift_parallel.py
arctic_inference/vllm/spec_decoding.py
arctic_inference/vllm/spec_dec/__init__.py
arctic_inference/vllm/spec_dec/arctic_proposer.py
arctic_inference/vllm/spec_dec/arctic_speculator.py
arctic_inference/vllm/spec_dec/fp8.py
arctic_inference/vllm/spec_dec/logits_processor_opt.py
arctic_inference/vllm/spec_dec/vocab_parallel_embedding.py
arctic_inference/vllm/swiftkv/__init__.py
arctic_inference/vllm/swiftkv/linear.py
arctic_inference/vllm/swiftkv/llama_swiftkv.py
csrc/custom_ops/CMakeLists.txt
csrc/custom_ops/attention_generic.cuh
csrc/custom_ops/custom_ops.h
csrc/custom_ops/dispatch_utils.h
csrc/custom_ops/dtype_fp8.cuh
csrc/custom_ops/kernels.cu
csrc/custom_ops/quant_utils.cuh
csrc/custom_ops/torch_bindings.cpp
csrc/suffix_cache/CMakeLists.txt
csrc/suffix_cache/pybind.cc
csrc/suffix_cache/suffix_tree.cc
csrc/suffix_cache/suffix_tree.h
tests/test_custom_ops.py
tests/test_patching.py