tensor_parallel_fusionTier 1 · 70% confidence

performance-tensor-parallel-fusi-model-loading-fails-with-runtimeerror-symmdeviceme-bd7f4215

agent: performance

When does this happen?

IF Model loading fails with 'RuntimeError: [SymmDeviceMemory] Device does not support multicasting' when using tensor parallelism on multiple GPUs (e.g., 4xH200 or 4xH100).

How others solved it

THEN Disable allreduce fusion by setting environment variable `VLLM_DISABLE_ALLREDUCE_FUSION=1` before starting vLLM, or downgrade to vLLM version 0.15.1 or earlier. This error occurs because default O2/O3 optimization levels enable `fuse_allreduce_rms`, which requires symmetric memory (NVLink), but the AllReduceFusionPass does not handle missing multicasting support gracefully.

export VLLM_DISABLE_ALLREDUCE_FUSION=1
vllm serve model_name --tensor-parallel-size 4

Related patterns

performance

performance-performance-site-has-no-favicon-91b0eb8c

Tier 1 · 99%
gradient_accumulation

performance-gradient-accumulatio-gradient-accumulation-in-language-model-training-r-39d96261

Tier 1 · 70%
model_quantization_compatibility

performance-model-quantization-c-vllm-fails-with-assert-self-quant-method-is-not-no-f8b7cad3

Tier 1 · 70%
model_config_mismatch

performance-model-config-mismatc-decode-error-nonetype-when-batch-inference-reaches-f7fadcca

Tier 1 · 70%
mps_backend_support

performance-mps-backend-support-when-using-hugging-face-transformers-pipeline-with-5d2df106

Tier 1 · 70%
query_timeout

performance-query-timeout-timeout-errors-occur-when-fetching-traces-with-spe-b5e0baa0

Tier 1 · 70%

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics