Logo
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
…
Powered by Gitea Version: 1.27.2 Page: 1678ms Template: 7ms
Auto
English
Bahasa Indonesia Deutsch English Español Français Gaeilge Italiano Latviešu Magyar nyelv Nederlands Polski Português de Portugal Português do Brasil Suomi Svenska Türkçe Čeština Ελληνικά Български Русский Українська فارسی മലയാളം 日本語 简体中文 繁體中文(台灣) 繁體中文(香港) 한국어
Licenses API