LICENSE
README.md
pyproject.toml
src/wllm/__init__.py
src/wllm/cli.py
src/wllm/api/__init__.py
src/wllm/api/auth.py
src/wllm/api/logging_config.py
src/wllm/api/metrics.py
src/wllm/api/rate_limit.py
src/wllm/api/schemas.py
src/wllm/api/server.py
src/wllm/api/stop_strings.py
src/wllm/api/tool_calls.py
src/wllm/baseline/__init__.py
src/wllm/baseline/generate.py
src/wllm/baseline/model.py
src/wllm/engine/__init__.py
src/wllm/engine/async_engine.py
src/wllm/engine/beam_search.py
src/wllm/engine/cuda_graph_decoder.py
src/wllm/engine/detokenizer.py
src/wllm/engine/embeddings.py
src/wllm/engine/guided_decoding.py
src/wllm/engine/kv_cache.py
src/wllm/engine/lora.py
src/wllm/engine/sampling.py
src/wllm/engine/scheduler.py
src/wllm/engine/sequence.py
src/wllm/engine/speculative.py
src/wllm/kernels/__init__.py
src/wllm/kernels/_msvc_env.py
src/wllm/kernels/paged_attention.py
src/wllm/kernels/csrc/paged_attention.cu
src/wllm/kernels/csrc/vector_add.cu
src/wllm/models/__init__.py
src/wllm/models/config.py
src/wllm/models/gemma.py
src/wllm/models/llama.py
src/wllm/models/qwen2.py
src/wllm/models/registry.py
src/wllm/quant/__init__.py
src/wllm/quant/dequant.py
src/wllm/quant/gguf_loader.py
src/wllm/quant/quant_linear.py
src/wllm_server.egg-info/PKG-INFO
src/wllm_server.egg-info/SOURCES.txt
src/wllm_server.egg-info/dependency_links.txt
src/wllm_server.egg-info/entry_points.txt
src/wllm_server.egg-info/requires.txt
src/wllm_server.egg-info/top_level.txt
tests/test_async_engine.py
tests/test_baseline.py
tests/test_beam_search.py
tests/test_chunked_prefill.py
tests/test_chunked_prefill_scheduler.py
tests/test_cpu_inference.py
tests/test_cpu_swap.py
tests/test_cuda_graph_decoder.py
tests/test_decode_graphable.py
tests/test_detokenizer.py
tests/test_embeddings.py
tests/test_gemma_architecture.py
tests/test_gguf_dequant.py
tests/test_gguf_loader.py
tests/test_guided_decoding.py
tests/test_guided_decoding_scheduler.py
tests/test_kv_cache.py
tests/test_llama_architecture.py
tests/test_lora.py
tests/test_lora_integration.py
tests/test_native_model.py
tests/test_paged_attention_kernel.py
tests/test_paged_generation.py
tests/test_prefix_caching.py
tests/test_sampling.py
tests/test_sampling_integration.py
tests/test_scheduler.py
tests/test_scheduler_cuda_graphs.py
tests/test_server.py
tests/test_server_beam_search.py
tests/test_server_hardening.py
tests/test_server_lora.py
tests/test_speculative_decoding.py
tests/test_speculative_ngram.py
tests/test_stop_strings.py
tests/test_tool_calls.py