Add transfer queue admission knobs
This commit is contained in:
@@ -197,6 +197,26 @@ def main() -> None:
|
||||
"Use a negative value to disable this filter."
|
||||
),
|
||||
)
|
||||
replay.add_argument(
|
||||
"--kvcache-seed-max-decode-transfer-queue-reqs",
|
||||
type=int,
|
||||
default=None,
|
||||
help=(
|
||||
"For kvcache-centric worker admission, skip seed/reseed when the "
|
||||
"target D reports more transfer-queue requests than this value. "
|
||||
"Use a negative value to disable this filter."
|
||||
),
|
||||
)
|
||||
replay.add_argument(
|
||||
"--kvcache-direct-max-decode-transfer-queue-reqs",
|
||||
type=int,
|
||||
default=None,
|
||||
help=(
|
||||
"For kvcache-centric worker admission, skip direct-to-D append when "
|
||||
"the target D reports more transfer-queue requests than this value. "
|
||||
"Use a negative value to disable this filter."
|
||||
),
|
||||
)
|
||||
replay.add_argument(
|
||||
"--kvcache-prefill-priority-eviction",
|
||||
action="store_true",
|
||||
@@ -389,6 +409,26 @@ def main() -> None:
|
||||
"Use a negative value to disable this filter."
|
||||
),
|
||||
)
|
||||
benchmark.add_argument(
|
||||
"--kvcache-seed-max-decode-transfer-queue-reqs",
|
||||
type=int,
|
||||
default=None,
|
||||
help=(
|
||||
"For kvcache-centric worker admission, skip seed/reseed when the "
|
||||
"target D reports more transfer-queue requests than this value. "
|
||||
"Use a negative value to disable this filter."
|
||||
),
|
||||
)
|
||||
benchmark.add_argument(
|
||||
"--kvcache-direct-max-decode-transfer-queue-reqs",
|
||||
type=int,
|
||||
default=None,
|
||||
help=(
|
||||
"For kvcache-centric worker admission, skip direct-to-D append when "
|
||||
"the target D reports more transfer-queue requests than this value. "
|
||||
"Use a negative value to disable this filter."
|
||||
),
|
||||
)
|
||||
benchmark.add_argument(
|
||||
"--kvcache-prefill-priority-eviction",
|
||||
action="store_true",
|
||||
@@ -456,6 +496,18 @@ def main() -> None:
|
||||
if args.kvcache_seed_max_inflight_decode < 0
|
||||
else args.kvcache_seed_max_inflight_decode
|
||||
),
|
||||
kvcache_seed_max_decode_transfer_queue_reqs=(
|
||||
None
|
||||
if args.kvcache_seed_max_decode_transfer_queue_reqs is None
|
||||
or args.kvcache_seed_max_decode_transfer_queue_reqs < 0
|
||||
else args.kvcache_seed_max_decode_transfer_queue_reqs
|
||||
),
|
||||
kvcache_direct_max_decode_transfer_queue_reqs=(
|
||||
None
|
||||
if args.kvcache_direct_max_decode_transfer_queue_reqs is None
|
||||
or args.kvcache_direct_max_decode_transfer_queue_reqs < 0
|
||||
else args.kvcache_direct_max_decode_transfer_queue_reqs
|
||||
),
|
||||
kvcache_prefill_priority_eviction=(
|
||||
args.kvcache_prefill_priority_eviction
|
||||
),
|
||||
@@ -582,6 +634,18 @@ def main() -> None:
|
||||
if args.kvcache_seed_max_inflight_decode < 0
|
||||
else args.kvcache_seed_max_inflight_decode
|
||||
),
|
||||
kvcache_seed_max_decode_transfer_queue_reqs=(
|
||||
None
|
||||
if args.kvcache_seed_max_decode_transfer_queue_reqs is None
|
||||
or args.kvcache_seed_max_decode_transfer_queue_reqs < 0
|
||||
else args.kvcache_seed_max_decode_transfer_queue_reqs
|
||||
),
|
||||
kvcache_direct_max_decode_transfer_queue_reqs=(
|
||||
None
|
||||
if args.kvcache_direct_max_decode_transfer_queue_reqs is None
|
||||
or args.kvcache_direct_max_decode_transfer_queue_reqs < 0
|
||||
else args.kvcache_direct_max_decode_transfer_queue_reqs
|
||||
),
|
||||
kvcache_prefill_priority_eviction=(
|
||||
args.kvcache_prefill_priority_eviction
|
||||
),
|
||||
|
||||
Reference in New Issue
Block a user