This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
2
Packages
Projects
Releases
Wiki
Activity
Files
78300cdabffbaaffe7625ed34412ec2aec75535c
vLLM
/
vllm
/
distributed
/
eplb
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
..
policy
[EPLB] Simplify EPLB rearrange by only returning one map (
#36267
)
2026-03-18 20:34:00 -04:00
__init__.py
Abstract eplb algo (
#26471
)
2025-12-04 19:09:09 +00:00
async_worker.py
[EPLB] Enable nixl eplb communicator for elastic ep (
#45013
)
2026-06-22 10:54:08 -07:00
eplb_communicator.py
[NIXL] Use int32 array for indices to avoid intermediate conversion (
#51952
)
2026-09-02 16:30:16 +02:00
eplb_state.py
[Elastic EP] Reduce eager-mode reconfiguration downtime (
#51885
)
2026-08-19 02:13:06 +00:00
eplb_utils.py
Revert "[Platform] Replace
torch.cuda.Event
with
torch.Event
(
#47140
)" (
#47668
)
2026-07-06 14:18:33 +01:00
rebalance_execute.py
[Core] Check for GPU<->CPU syncs during CI (
#43107
)
2026-08-14 17:42:05 -07:00