Sage Mooreandyoukaichao 9a88f89799 custom allreduce + torch.compile (#10121) ...

Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>

2024-11-25 22:00:16 -08:00

..

__init__.py

[Core][Refactor] move parallel_utils into vllm/distributed (#3950)

2024-04-10 15:33:30 -07:00

cuda_wrapper.py

[core][misc] update libcudart finding (#7620)

2024-08-16 23:01:35 -07:00

custom_all_reduce_utils.py

[CI/Build] drop support for Python 3.8 EOL (#8464)

2024-11-06 07:11:55 +00:00

custom_all_reduce.py

[Core][Distributed] Refactor ipc buffer init in CustomAllreduce (#10030)

2024-11-06 23:50:47 -08:00

hpu_communicator.py

[Hardware][Intel-Gaudi] Add Intel Gaudi (HPU) inference backend (#6143)

2024-11-06 01:09:10 -08:00

pynccl_wrapper.py

[Misc] Add pynccl wrappers for all_gather and reduce_scatter (#9432)

2024-11-22 22:14:03 -05:00

pynccl.py

custom allreduce + torch.compile (#10121)

2024-11-25 22:00:16 -08:00

shm_broadcast.py

[Core] Use os.sched_yield in ShmRingBuffer instead of time.sleep (#9994)

2024-11-05 01:08:21 +00:00

tpu_communicator.py

[TPU] Support single and multi-host TPUs on GKE (#7613)

2024-08-30 00:27:40 -07:00

xpu_communicator.py

[Bugfix][XPU] Fix xpu tp by introducing XpuCommunicator (#10144)

2024-11-08 09:41:03 +00:00