This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
1
Packages
Projects
Releases
Wiki
Activity
Files
78300cdabffbaaffe7625ed34412ec2aec75535c
vLLM
/
tests
/
v1
/
kv_offload
/
tiering
T
History
Ilia Yastrebov
41848caa63
[NIXL] Use int32 array for indices to avoid intermediate conversion (
#51952
)
...
Signed-off-by: Ilia Yastrebov <
iyastrebov@nvidia.com
>
2026-09-02 16:30:16 +02:00
..
p2p
[Bugfix][KV Offload][P2P] Preserve aborted loads until abort completion (
#52571
)
2026-08-31 14:34:48 +03:00
__init__.py
[Test][KV Offloading] Add unit tests for OffloadingSpecFactory and SecondaryTierFactory (
#46355
)
2026-06-22 17:45:04 +03:00
test_async_lookup.py
[Bugfix][KV Offload] Ignore stale async lookup results (
#54872
)
2026-09-02 17:10:26 +03:00
test_factory.py
[KV Offload] Support out-of-tree secondary tier managers via
module_path
(
#51007
)
2026-08-05 20:30:53 +03:00
test_fs_tier.py
[KV Offload] Expose data-parallel topology to offloading backends (
#51879
)
2026-08-12 20:27:26 -07:00
test_metrics.py
Add tiering offloading metrics (
#48798
)
2026-08-10 05:23:14 +03:00
test_obj_tier.py
[NIXL] Use int32 array for indices to avoid intermediate conversion (
#51952
)
2026-09-02 16:30:16 +02:00
test_tiering_offloading.py
[Bugfix][KVOffload] P2P tier declares REQUEST_LEVEL on the producer leg (
#52912
)
2026-08-31 10:07:20 +00:00