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
235366fe2eb3144321978e181af94487f0215595
vLLM
/
vllm
/
distributed
/
device_communicators
T
History
Tyler Michael Smith
04bbf38e05
[Core] Use os.sched_yield in ShmRingBuffer instead of time.sleep (
#9994
)
...
Signed-off-by: Tyler Michael Smith <
tyler@neuralmagic.com
>
2024-11-05 01:08:21 +00:00
..
__init__.py
[Core][Refactor] move parallel_utils into vllm/distributed (
#3950
)
2024-04-10 15:33:30 -07:00
cuda_wrapper.py
[core][misc] update libcudart finding (
#7620
)
2024-08-16 23:01:35 -07:00
custom_all_reduce_utils.py
[misc] fix custom allreduce p2p cache file generation (
#7853
)
2024-08-26 15:02:25 -07:00
custom_all_reduce.py
[core][distributed] fix custom allreduce in pytorch 2.5 (
#9815
)
2024-10-29 17:06:24 -07:00
pynccl_wrapper.py
[mypy] Enable type checking for test directory (
#5017
)
2024-06-15 04:45:31 +00:00
pynccl.py
[Distributed] Add send and recv helpers (
#5719
)
2024-06-23 14:42:28 -07:00
shm_broadcast.py
[Core] Use os.sched_yield in ShmRingBuffer instead of time.sleep (
#9994
)
2024-11-05 01:08:21 +00:00
tpu_communicator.py
[TPU] Support single and multi-host TPUs on GKE (
#7613
)
2024-08-30 00:27:40 -07:00