[Core][Bugfix][Perf] Introduce MQLLMEngine to avoid asyncio OH (#8157)

Co-authored-by: Nick Hill <nickhill@us.ibm.com>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
This commit is contained in:
Alexander Matveev
2024-09-18 13:56:58 +00:00
committed by GitHub
co-authored by Nick Hill rshaw@neuralmagic.com <rshaw@neuralmagic.com> Robert Shaw Simon Mo
parent 9d104b5beb
commit 7c7714d856
36 changed files with 1464 additions and 1169 deletions
+1
View File
@@ -1289,6 +1289,7 @@ class LLMEngine:
# torch.distributed ops which may otherwise timeout, and unblocks
# the RPC thread in the workers so that they can process any other
# queued control plane messages, such as add/remove lora adapters.
logger.debug("Stopping remote worker execution loop.")
self.model_executor.stop_remote_worker_execution_loop()
return ctx.request_outputs