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
af826e082045e8bcd3ab2ea3129bcf91da7d58de
vLLM
/
vllm
/
platforms
T
History
Wentao Ye
5b0448104f
[Bug] Raise error explicitly if using incompatible backend (
#27424
)
...
Signed-off-by: yewentao256 <
zhyanwentao@126.com
>
2025-10-29 13:29:20 -04:00
..
__init__.py
[Misc] Clean up more utils (
#27567
)
2025-10-27 15:30:38 +00:00
cpu.py
[cpu][perf] Fix low CPU utilization with VLLM_CPU_OMP_THREADS_BIND on AArch64 (
#27415
)
2025-10-27 11:14:55 +00:00
cuda.py
[Bug] Raise error explicitly if using incompatible backend (
#27424
)
2025-10-29 13:29:20 -04:00
interface.py
[Bugfix] Limit the default value of
max_model_len
when it is not specified by users (
#27556
)
2025-10-27 10:16:20 +00:00
rocm.py
[ROCm][Platform] Add MI308X device id in _ROCM_DEVICE_ID_NAME_MAP (
#27623
)
2025-10-29 14:44:03 +00:00
tpu.py
[Bugfix] Limit the default value of
max_model_len
when it is not specified by users (
#27556
)
2025-10-27 10:16:20 +00:00
xpu.py
[NIXL] use Host buffer to support TP_ratio > 1 for XPU (
#27140
)
2025-10-22 15:28:13 +00:00