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>
Installation
vLLM supports the following hardware platforms:
Hardware Plugins
vLLM supports third-party hardware plugins that live outside the main vllm repository. These follow the Hardware-Pluggable RFC.
A list of all supported hardware can be found on the vLLM website, see Universal Compatibility - Hardware.
If you want to add new hardware, please contact us on Slack or Email.