This website requires JavaScript.
Explore
Help
Register
Sign In
squall
/
vllm
Watch
1
Star
0
Fork
0
You've already forked vllm
Code
Issues
Pull Requests
Actions
1
Packages
Projects
Releases
Wiki
Activity
fd4ea8ef5c
vllm
/
tests
/
kernels
History
Zhuohan Li
fd4ea8ef5c
Use NCCL instead of ray for control-plane communication to remove serialization overhead (
#2221
)
2024-01-03 11:30:22 -08:00
..
conftest.py
[FIX] Support non-zero CUDA devices in custom kernels (
#1959
)
2024-01-02 19:09:59 -08:00
test_activation.py
[FIX] Support non-zero CUDA devices in custom kernels (
#1959
)
2024-01-02 19:09:59 -08:00
test_attention.py
[FIX] Support non-zero CUDA devices in custom kernels (
#1959
)
2024-01-02 19:09:59 -08:00
test_cache.py
Use NCCL instead of ray for control-plane communication to remove serialization overhead (
#2221
)
2024-01-03 11:30:22 -08:00
test_layernorm.py
[FIX] Support non-zero CUDA devices in custom kernels (
#1959
)
2024-01-02 19:09:59 -08:00
test_pos_encoding.py
[FIX] Support non-zero CUDA devices in custom kernels (
#1959
)
2024-01-02 19:09:59 -08:00