[P/D] NIXL Integration (#17751)

Signed-off-by: ApostaC <yihua98@uchicago.edu>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Signed-off-by: Robert Shaw <rshaw@neuralmagic.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Brent Salisbury <bsalisbu@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: ApostaC <yihua98@uchicago.edu>
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Brent Salisbury <bsalisbu@redhat.com>
This commit is contained in:
Robert Shaw
2025-05-12 12:46:16 -04:00
committed by GitHub
parent 05a4324f8e
commit d19110204c
34 changed files with 2723 additions and 108 deletions

View File

@@ -182,6 +182,15 @@ class EngineCore:
# Start grammar compilation asynchronously
self.structured_output_manager.grammar_init(req)
if req.raw_kv_transfer_params is not None:
if (kv_connector := self.scheduler.get_kv_connector()):
# Parse raw KV transfer params via connector.
kv_connector.set_kv_transfer_params(req)
else:
logger.warning(
"Got KVTransferParams, but no KVConnector found. "
"Disabling KVTransfer for this request.")
self.scheduler.add_request(req)
def abort_requests(self, request_ids: list[str]):