LICENSE
MANIFEST.in
README.md
pyproject.toml
requirements-dev.txt
requirements.txt
setup.py
dfastllm/__init__.py
dfastllm/cli.py
dfastllm/config.py
dfastllm/version.py
dfastllm.egg-info/PKG-INFO
dfastllm.egg-info/SOURCES.txt
dfastllm.egg-info/dependency_links.txt
dfastllm.egg-info/entry_points.txt
dfastllm.egg-info/requires.txt
dfastllm.egg-info/top_level.txt
dfastllm/engine/__init__.py
dfastllm/engine/adaptive_steps.py
dfastllm/engine/advanced_sampling.py
dfastllm/engine/apd.py
dfastllm/engine/attention_cache.py
dfastllm/engine/base.py
dfastllm/engine/block_attention.py
dfastllm/engine/compile_wrapper.py
dfastllm/engine/consistency.py
dfastllm/engine/continuous_batching.py
dfastllm/engine/dfastllm_engine.py
dfastllm/engine/diffusion_sampler.py
dfastllm/engine/entropy_controller.py
dfastllm/engine/flash_attention_wrapper.py
dfastllm/engine/hybrid_engine.py
dfastllm/engine/mor_decoder.py
dfastllm/engine/optimized_core.py
dfastllm/engine/outputs.py
dfastllm/engine/paged_attention.py
dfastllm/engine/quantization.py
dfastllm/engine/request_queue.py
dfastllm/engine/sampling_params.py
dfastllm/engine/speculative_decoder.py
dfastllm/engine/streaming_llm.py
dfastllm/engine/tensor_parallel.py
dfastllm/engine/tokenizer.py
dfastllm/engine/core/__init__.py
dfastllm/engine/diffusion/__init__.py
dfastllm/engine/hybrid/__init__.py
dfastllm/engine/optimization/__init__.py
dfastllm/engine/parallel/__init__.py
dfastllm/engine/v2/__init__.py
dfastllm/entrypoints/__init__.py
dfastllm/entrypoints/launcher.py
dfastllm/entrypoints/openai/__init__.py
dfastllm/entrypoints/openai/api_server.py
dfastllm/entrypoints/openai/protocol.py
dfastllm/entrypoints/openai/serving_chat.py
dfastllm/entrypoints/openai/serving_completion.py
dfastllm/metrics/__init__.py
dfastllm/metrics/prometheus.py
dfastllm/serving/__init__.py
dfastllm/serving/disaggregated.py
dfastllm/serving/streaming.py
dfastllm/tests/test_optimizations.py