Triton Python, C++ and Java client libraries, and GRPC-generated client examples for go, java and scala.
BSD 3-Clause "New" or "Revised" License
520
stars
225
forks
source link
Patch vLLM for missing content entry #671
Closed
IzzyPutterman closed 1 month ago
vLLM does not include content in the first response from the server. Now we filter for the content entry missing before preprocessing merged requests.