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
4068f4b5b5dc5e2d1114be0cbb126bc44fb4e906
vLLM/vllm/distributed
T
History
Yan Burman 300acb8347 [Core][Bugfix] Use correct device to initialize GPU data during CUDA-graph-capture (#11233)
Signed-off-by: Yan Burman <yanburman@users.noreply.github.com>
Signed-off-by: Ido Asraff <idoa@atero.ai>
2025-01-04 14:50:16 +08:00
..
device_communicators
[core][distributed] initialization from StatelessProcessGroup (#10986)
2024-12-12 09:04:19 +00:00
kv_transfer
[Misc] KV cache transfer connector registry (#11481)
2024-12-29 16:08:09 +00:00
__init__.py
[Core][Refactor] move parallel_utils into vllm/distributed (#3950)
2024-04-10 15:33:30 -07:00
communication_op.py
[Bugfix] Fix weight loading for Chameleon when TP>1 (#7410)
2024-08-13 05:33:41 +00:00
parallel_state.py
[Core][Bugfix] Use correct device to initialize GPU data during CUDA-graph-capture (#11233)
2025-01-04 14:50:16 +08:00
utils.py
[core][distributed] use tcp store directly (#10275)
2024-11-12 17:36:08 -08:00
Powered by Gitea Version: 1.27.2 Page: 166ms Template: 6ms
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