Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1.2 KiB
Summary
!!! important
Many decoder language models can now be automatically loaded using the Transformers modeling backend without having to implement them in vLLM. See if vllm serve <model> works first!
vLLM models are specialized PyTorch models that take advantage of various features to optimize their performance.
The complexity of integrating a model into vLLM depends heavily on the model's architecture. The process is considerably straightforward if the model shares a similar architecture with an existing model in vLLM. However, this can be more complex for models that include new operators (e.g., a new attention mechanism).
Read through these pages for a step-by-step guide:
!!! tip If you are encountering issues while integrating your model into vLLM, feel free to open a GitHub issue or ask on our developer slack. We will be happy to help you out!