Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Signed-off-by: Harry Mellor <hej.mellor@gmail.com> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Disaggregated Prefill V1
This example contains scripts that demonstrate disaggregated prefill in the offline setting of vLLM.
Files
run.sh- A helper script that will runprefill_example.pyanddecode_example.pysequentially.- Make sure you are in the
examples/disaggregated/example_connectordirectory before runningrun.sh.
- Make sure you are in the
prefill_example.py- A script which performs prefill only, saving the KV state to thelocal_storagedirectory and the prompts tooutput.txt.decode_example.py- A script which performs decode only, loading the KV state from thelocal_storagedirectory and the prompts fromoutput.txt.