5 posts
How vLLM developers debug hanging and complex CUDA kernels by triggering GPU core dumps, identifying stuck kernels, and mapping failures back to source code lines for faster kernel debugging.
How the vLLM plugin system helps teams customize scheduling, KV-cache behavior, hardware integrations, and model execution without long-lived forks, monkey patches, or brittle internal modifications.
How vLLM debugged Kimi K2 tool-calling accuracy, covering chat-template compatibility, add_generation_prompt handling, schema validation failures, benchmark fixes, and tool-use reliability.
How to debug vLLM CUDA illegal memory access errors with CUDA core dumps, environment variables, cuda-gdb, and GPU state inspection when Python stack traces or CUDA_LAUNCH_BLOCKING are insufficient.
How to install and develop vLLM using stable releases, nightly wheels, uv, source builds, Python and C++/CUDA workflows, and version tracking for production deployments.
