biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V0 deprecation] Deprecate V0 Neuron backend (#21159)

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon
2025-09-06 16:15:18 -07:00
committed by GitHub
parent 848562bd49
commit 4172235ab7
46 changed files with 10 additions and 5462 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/config/parallel.py
View File

@@ -377,10 +377,7 @@ class ParallelConfig:
from vllm.executor import ray_utils
backend: DistributedExecutorBackend = "mp"
ray_found = ray_utils.ray_is_available()
if current_platform.is_neuron():
# neuron uses single process to control multiple devices
backend = "uni"
elif current_platform.is_tpu() and envs.VLLM_XLA_USE_SPMD:
if current_platform.is_tpu() and envs.VLLM_XLA_USE_SPMD:
backend = "uni"
elif (current_platform.is_cuda()
and cuda_device_count_stateless() < self.world_size):