This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
2
Packages
Projects
Releases
Wiki
Activity
Files
bb8dab821e00ffdc1007b8b11edbcab6bcfa4140
vLLM
/
vllm
/
platforms
T
History
Ilya Markov
and
ilmarkov
ef608c37a7
[Distributed] [ROCM] Fix custom allreduce enable checks (
#16010
)
...
Signed-off-by: ilmarkov <
imarkov@redhat.com
> Co-authored-by: ilmarkov <
imarkov@redhat.com
>
2025-04-04 09:39:08 -07:00
..
__init__.py
Remove openvino support in favor of external plugin (
#15339
)
2025-03-22 14:06:39 -07:00
cpu.py
[CPU] Change default block_size for CPU backend (
#16002
)
2025-04-04 09:39:05 -07:00
cuda.py
[Distributed] [ROCM] Fix custom allreduce enable checks (
#16010
)
2025-04-04 09:39:08 -07:00
hpu.py
[platform] add base class for communicators (
#13208
)
2025-02-16 22:14:22 +08:00
interface.py
[Distributed] [ROCM] Fix custom allreduce enable checks (
#16010
)
2025-04-04 09:39:08 -07:00
neuron.py
[Neuron] Add Neuron device communicator for vLLM v1 (
#14085
)
2025-03-10 18:37:04 -07:00
rocm.py
[Distributed] [ROCM] Fix custom allreduce enable checks (
#16010
)
2025-04-04 09:39:08 -07:00
tpu.py
[bugfix] add supports_v1 platform interface (
#15417
)
2025-03-25 15:00:32 -04:00
xpu.py
[Misc][XPU] Use None as device capacity for XPU (
#14932
)
2025-03-17 01:22:14 -07:00