Ilya Markov 1788aa1efb

[BugFix] Graceful handling of torch symm mem errors. (#27671) ...

Signed-off-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

2025-11-11 17:41:54 -07:00

..

__init__.py

…

all2all.py

[Refactor] Remove VLLM_DEEPEP_LOW_LATENCY_ALLOW_NVLINK (#27750)

2025-10-30 15:32:39 -04:00

all_reduce_utils.py

[Chore] Separate out system utilities from vllm.utils (#27201)

2025-10-22 20:25:25 +00:00

base_device_communicator.py

[Kernels] Isolate modular kernel code from FusedMoEMethodBase subclasses. (#27123)

2025-11-04 21:59:45 +08:00

cpu_communicator.py

…

cuda_communicator.py

[Log] Optimize Startup Log (#26740)

2025-10-24 19:27:04 -04:00

cuda_wrapper.py

…

custom_all_reduce.py

[Log] Optimize Startup Log (#26740)

2025-10-24 19:27:04 -04:00

mnnvl_compat.py

…

pynccl_allocator.py

[Chore] Separate out NCCL utilities from vllm.utils (#27197)

2025-10-21 06:18:23 -07:00

pynccl_wrapper.py

[Chore] Separate out NCCL utilities from vllm.utils (#27197)

2025-10-21 06:18:23 -07:00

pynccl.py

[Log] Optimize Startup Log (#26740)

2025-10-24 19:27:04 -04:00

quick_all_reduce.py

[Chore] Clean up pytorch helper functions in vllm.utils (#26908)

2025-10-18 09:48:22 -07:00

ray_communicator.py

[Misc] Avoid "PyTorch non-writable tensors" warning in RayPPCommunicator (#27443)

2025-10-24 14:53:09 +08:00

shm_broadcast.py

[Log] update shm wait time msg (#28255)

2025-11-07 09:43:30 -05:00

shm_object_storage.py

[Bugfix] Fix allocation & free logic of SingleWriterShmRingBuffer (#27117)

2025-10-28 15:01:24 +00:00

symm_mem.py

[BugFix] Graceful handling of torch symm mem errors. (#27671)

2025-11-11 17:41:54 -07:00

tpu_communicator.py

[V0 Deprecation] Remove V0 executors (#27142)

2025-10-21 11:09:37 -07:00

xpu_communicator.py

[UX] Replace VLLM_ALL2ALL_BACKEND with --all2all-backend (#26732)

2025-10-13 18:12:52 -07:00