REFERENCES.md

📑 Page 1. 📑

• [1] https://github.com/Zerohertz

📑 Page 3. 📑

• [2] https://github.com/Zerohertz/PyCon_KR_2025_Tutorial_vLLM

📑 Page 4. 📑

• [3] vllm-project/vllm#1441

📑 Page 7. 📑

• [4] https://artificialanalysis.ai/

📑 Page 10. 📑

• [5] https://github.com/vllm-project/vllm/commit/e7d9d9c08c79b386f6d0477e87b77a572390317d
• [6] https://github.com/vllm-project/vllm/commit/0b98ba15c744f1dfb0ea4f2135e85ca23d572ae1
• [7] https://arxiv.org/abs/2309.06180
• [8] https://github.com/vllm-project/vllm/blob/main/LICENSE
• [9] vllm-project/vllm#835

📑 Page 11. 📑

• [10] https://www.star-history.com/

📑 Page 13. 📑

• [11] https://github.com/vllm-project/flash-attention
• [12] https://github.com/flashinfer-ai/flashinfer
• [13] https://docs.vllm.ai/en/v0.9.2/configuration/optimization.html#chunked-prefill_1
• [14] https://docs.vllm.ai/en/v0.9.2/features/spec_decode.html

📑 Page 15. 📑

• [15] https://docs.vllm.ai/en/v0.9.2/deployment/docker.html

📑 Page 16. 📑

• [16] https://docs.vllm.ai/en/v0.9.2/serving/openai_compatible_server.html
• [17] https://platform.openai.com/docs/api-reference/models/list
• [18] https://platform.openai.com/docs/api-reference/chat/create

📑 Page 17. 📑

• [19] https://github.com/openai/openai-python/blob/v1.97.1/src/openai/types/shared_params/function_definition.py#L13-L45

📑 Page 18. 📑

• [20] https://docs.vllm.ai/en/v0.9.2/features/tool_calling.html
• [21] https://qwen.readthedocs.io/en/latest/deployment/vllm.html#parsing-tool-calls

📑 Page 19. 📑

• [22] https://docs.vllm.ai/en/v0.9.2/features/structured_outputs.html
• [23] https://github.com/vllm-project/vllm/blob/v0.9.2/vllm/entrypoints/openai/protocol.py#L247-L252
• [24] https://github.com/vllm-project/vllm/blob/v0.9.2/vllm/entrypoints/openai/protocol.py#L497-L506
• [25] https://github.com/vllm-project/vllm/blob/v0.9.2/vllm/entrypoints/openai/protocol.py#L538
• [26] https://github.com/vllm-project/vllm/blob/v0.9.2/vllm/engine/async_llm_engine.py#L473-L484
• [27] https://github.com/vllm-project/vllm/blob/v0.9.2/vllm/model_executor/guided_decoding/__init__.py#L100-L139
• [28] vllm-project/vllm#22740
• [29] vllm-project/vllm#22772

📑 Page 21. 📑

• [30] https://docs.vllm.ai/en/v0.9.2/features/reasoning_outputs.html
• [31] https://qwen.readthedocs.io/en/latest/deployment/vllm.html#parsing-thinking-content
• [32] https://github.com/vllm-project/vllm/blob/v0.9.2/vllm/engine/arg_utils.py#L626-L634

📑 Page 22. 📑

• [33] https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/tokenizer_config.json#L230

📑 Page 23. 📑

• [34] https://docs.vllm.ai/en/v0.9.2/serving/openai_compatible_server.html#chat-template_1
• [35] https://github.com/vllm-project/vllm/tree/main/examples

📑 Page 25. 📑

• [36] https://arxiv.org/abs/1706.03762
• [37] https://huggingface.co/blog/not-lain/kv-caching
• [38] https://docs.vllm.ai/en/v0.9.2/design/kernel/paged_attention.html
• [39] https://blog.vllm.ai/2023/06/20/vllm.html
• [40] https://github.com/HandsOnLLM/Hands-On-Large-Language-Models/blob/main/chapter03/Chapter%203%20-%20Looking%20Inside%20LLMs.ipynb

📑 Page 31. 📑

• [41] https://www.anyscale.com/blog/continuous-batching-llm-inference
• [42] https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/user_guide/batcher.html

📑 Page 33. 📑

• [43] https://docs.vllm.ai/en/v0.9.2/design/arch_overview.html
• [44] https://docs.vllm.ai/en/v0.9.2/usage/v1_guide.html
• [45] https://blog.vllm.ai/2025/01/27/v1-alpha-release.html
• [46] vllm-project/vllm#18571

📑 Page 36. 📑

• [47] https://zerohertz.github.io/vllm-openai-2/#Conclusion

📑 Page 38. 📑

• [48] https://docs.vllm.ai/en/v0.9.2/features/lora.html
• [49] https://arxiv.org/abs/2106.09685

📑 Page 40. 📑

• [50] https://docs.vllm.ai/en/v0.9.2/configuration/optimization.html#parallelism-strategies
• [51] https://www.youtube.com/watch?v=4i76hmmnJEo

📑 Page 42. 📑

• [52] https://docs.vllm.ai/en/v0.9.2/examples/online_serving/run_cluster.html
• [53] https://docs.vllm.ai/en/v0.9.2/usage/security.html
• [54] https://docs.pytorch.org/docs/stable/distributed.html#common-environment-variables
• [55] https://docs.nvidia.com/deeplearning/nccl/user-guide/docs/env.html#nccl-ib-disable

📑 Page 43. 📑

• [56] https://docs.vllm.ai/en/v0.9.2/serving/distributed_serving.html
• [57] https://blog.vllm.ai/2025/02/17/distributed-inference.html

📑 Page 44. 📑

• [58] https://zerohertz.github.io/distributed-computing-rdma-roce/
• [59] https://developer.nvidia.com/gpudirect

📑 Page 45. 📑

• [60] https://docs.vllm.ai/en/v0.9.2/serving/distributed_serving.html#gpudirect-rdma

📑 Page 46. 📑

• [61] https://docs.vllm.ai/en/v0.9.2/deployment/k8s.html
• [62] https://github.com/vllm-project/aibrix
• [63] https://arxiv.org/abs/2504.03648
• [64] https://blog.vllm.ai/2025/02/21/aibrix-release.html
• [65] https://aibrix.readthedocs.io/latest/
• [66] https://github.com/vllm-project/production-stack
• [67] https://docs.vllm.ai/en/v0.9.2/deployment/integrations/production-stack.html
• [68] https://blog.vllm.ai/2025/01/21/stack-release.html
• [69] https://blog.vllm.ai/production-stack/

📑 Page 47. 📑

• [70] https://docs.vllm.ai/en/v0.9.2/deployment/frameworks/lws.html
• [71] https://github.com/kubernetes-sigs/lws

📑 Page 48. 📑

• [72] https://docs.vllm.ai/en/v0.9.2/usage/metrics.html
• [73] https://docs.vllm.ai/en/v0.9.2/examples/online_serving/prometheus_grafana.html

📑 Page 49. 📑

• [74] https://docs.vllm.ai/en/v0.9.2/cli/index.html#bench
• [75] https://docs.vllm.ai/en/v0.9.2/contributing/profiling.html
• [76] https://github.com/vllm-project/vllm/tree/v0.9.2/benchmarks
• [77] https://github.com/vllm-project/guidellm
• [78] https://arxiv.org/pdf/2502.06494

📑 Page 50. 📑

• [79] vllm-project/vllm#11353
• [80] vllm-project/vllm#17652 (comment)
• [81] https://flashinfer.ai/2024/02/02/cascade-inference.html

📑 Page 52. 📑

• [82] vllm-project/vllm#20336

📑 Page 54. 📑

• [83] https://discuss.pytorch.kr/t/8-19-vllm-meetup/7401
• [84] https://lu.ma/cgcgprmh