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
d8037867313eef09779b265ea4bace76d2d118ba
vLLM
/
vllm
/
distributed
/
device_communicators
T
History
Russell Bryant
a0304dc504
[Security] Don't bind tcp zmq socket to all interfaces (
#17197
)
...
Signed-off-by: Russell Bryant <
rbryant@redhat.com
>
2025-04-28 10:08:20 -07:00
..
__init__.py
…
base_device_communicator.py
[Feature] support sequence parallelism using compilation pass (
#16155
)
2025-04-27 06:29:35 -07:00
cpu_communicator.py
[CPU][Bugfix] Using custom allreduce for CPU backend (
#15934
)
2025-04-02 07:46:47 -07:00
cuda_communicator.py
[Feature] support sequence parallelism using compilation pass (
#16155
)
2025-04-27 06:29:35 -07:00
cuda_wrapper.py
…
custom_all_reduce_utils.py
…
custom_all_reduce.py
[Distributed] Add custom allreduce support for ROCM (
#14125
)
2025-03-31 22:49:12 -07:00
hpu_communicator.py
…
neuron_communicator.py
[Neuron] Add Neuron device communicator for vLLM v1 (
#14085
)
2025-03-10 18:37:04 -07:00
pynccl_wrapper.py
…
pynccl.py
…
shm_broadcast.py
[Security] Don't bind tcp zmq socket to all interfaces (
#17197
)
2025-04-28 10:08:20 -07:00
tpu_communicator.py
[TPU] optimize the all-reduce performance (
#15903
)
2025-04-03 00:25:14 +00:00
xpu_communicator.py
…