README.md
pyproject.toml
src/m00_engine_loop.py
src/m01_continuous_batching.py
src/m02_token_budget.py
src/m03_paged_state.py
src/m04_chunked_prefill.py
src/m05_preemption.py
src/m06_prefix_hash.py
src/m07_radix_cache.py
src/inferris_lite/__init__.py
src/inferris_lite/__main__.py
src/inferris_lite/cli.py
src/inferris_lite.egg-info/PKG-INFO
src/inferris_lite.egg-info/SOURCES.txt
src/inferris_lite.egg-info/dependency_links.txt
src/inferris_lite.egg-info/entry_points.txt
src/inferris_lite.egg-info/top_level.txt
src/m08_cache_aware_scheduling/__init__.py
src/m08_cache_aware_scheduling/a_write_side/__init__.py
src/m08_cache_aware_scheduling/a_write_side/engine.py
src/m08_cache_aware_scheduling/a_write_side/pool.py
src/m08_cache_aware_scheduling/a_write_side/request.py
src/m08_cache_aware_scheduling/b_read_side/__init__.py
src/m08_cache_aware_scheduling/b_read_side/engine.py
src/m08_cache_aware_scheduling/b_read_side/pool.py
src/m08_cache_aware_scheduling/b_read_side/request.py
src/m08_cache_aware_scheduling/c_pressure_side/__init__.py
src/m08_cache_aware_scheduling/c_pressure_side/engine.py
src/m08_cache_aware_scheduling/c_pressure_side/pool.py
src/m08_cache_aware_scheduling/c_pressure_side/request.py
src/m09_speculative_decode/__init__.py
src/m09_speculative_decode/a_obligation/__init__.py
src/m09_speculative_decode/a_obligation/engine.py
src/m09_speculative_decode/a_obligation/request.py
src/m09_speculative_decode/b_verdict/__init__.py
src/m09_speculative_decode/b_verdict/engine.py
src/m09_speculative_decode/b_verdict/request.py
src/m09_speculative_decode/c_pages/__init__.py
src/m09_speculative_decode/c_pages/engine.py
src/m09_speculative_decode/c_pages/request.py
src/m10_executor_boundary/__init__.py
src/m10_executor_boundary/a_plan/__init__.py
src/m10_executor_boundary/a_plan/boundary.py
src/m10_executor_boundary/a_plan/engine.py
src/m10_executor_boundary/a_plan/executor.py
src/m10_executor_boundary/b_result/__init__.py
src/m10_executor_boundary/b_result/boundary.py
src/m10_executor_boundary/b_result/engine.py
src/m10_executor_boundary/b_result/executor.py
src/m10_executor_boundary/c_pages/__init__.py
src/m10_executor_boundary/c_pages/boundary.py
src/m10_executor_boundary/c_pages/engine.py
src/m10_executor_boundary/c_pages/executor.py
src/m11_parallelism/__init__.py
src/m11_parallelism/a_group/__init__.py
src/m11_parallelism/a_group/engine.py
src/m11_parallelism/a_group/group.py
src/m11_parallelism/b_ranked/__init__.py
src/m11_parallelism/b_ranked/engine.py
src/m11_parallelism/b_ranked/group.py
src/m11_parallelism/b_ranked/ranked.py
src/m11_parallelism/c_join/__init__.py
src/m11_parallelism/c_join/engine.py
src/m11_parallelism/c_join/group.py
src/m11_parallelism/c_join/ranked.py
tests/test_cli.py
tests/test_m00_engine_loop.py
tests/test_m01_continuous_batching.py
tests/test_m02_token_budget.py
tests/test_m03_paged_state.py
tests/test_m04_chunked_prefill.py
tests/test_m05_preemption.py
tests/test_m06_prefix_hash.py
tests/test_m07_radix_cache.py
tests/test_m08_cache_aware_scheduling.py
tests/test_m08a_write_side.py
tests/test_m08b_read_side.py
tests/test_m09_speculative_decode.py
tests/test_m09a_obligation.py
tests/test_m09b_verdict.py
tests/test_m10_executor_boundary.py
tests/test_m10a_plan.py
tests/test_m10b_result.py
tests/test_m11_parallelism.py
tests/test_m11a_group.py
tests/test_m11b_ranked.py