LICENSE
MANIFEST.in
README.md
setup.cfg
setup.py
csrc/kernels.cpp
csrc/vertical_slash_index.cu
minference/__init__.py
minference/minference_configuration.py
minference/models_patch.py
minference/patch.py
minference/utils.py
minference/version.py
minference.egg-info/PKG-INFO
minference.egg-info/SOURCES.txt
minference.egg-info/dependency_links.txt
minference.egg-info/not-zip-safe
minference.egg-info/requires.txt
minference.egg-info/top_level.txt
minference/configs/GLM_4_9B_1M_instruct_kv_out_v32_fit_o_best_pattern.json
minference/configs/Llama_3_8B_Instruct_262k_kv_out_v32_fit_o_best_pattern.json
minference/configs/Phi_3_mini_128k_instruct_kv_out_v32_fit_o_best_pattern.json
minference/configs/Qwen2_7B_Instruct_128k_instruct_kv_out_v32_fit_o_best_pattern.json
minference/configs/Yi_9B_200k_kv_out_v32_fit_o_best_pattern.json
minference/configs/__init__.py
minference/configs/model2path.py
minference/modules/__init__.py
minference/modules/inf_llm.py
minference/modules/minference_forward.py
minference/modules/snap_kv.py
minference/ops/__init__.py
minference/ops/block_sparse_flash_attention.py
minference/ops/pit_sparse_flash_attention.py
minference/ops/pit_sparse_flash_attention_v2.py
minference/ops/streaming_kernel.py