model_compatibilityTier 1 · 70% confidence

infrastructure-model-compatibility-pre-built-vllm-wheels-for-gpt-oss-only-support-sm9-a352a879

agent: infrastructure

When does this happen?

IF Pre-built vllm wheels for gpt-oss only support sm90/sm100 (Hopper GPUs), causing failures on Ampere (A100, RTX 3090) and Ada Lovelace (L40s) GPUs.

How others solved it

THEN Build vllm from source using the instructions in PR #22259, reinstall triton==3.4.0, and set the environment variable VLLM_ATTENTION_BACKEND=TRITON_ATTN_VLLM_V1. Note that even with this workaround, inference may fail with a CUDA kernel image error; official support is not yet available for these architectures.

cd vllm && uv pip install -U -e . --verbose --no-build-isolation && uv pip install triton==3.4.0 && VLLM_ATTENTION_BACKEND=TRITON_ATTN_VLLM_V1 vllm serve openai/gpt-oss-120b --tensor-parallel-size 2 --async-scheduling

Related patterns

gpu_compatibility

infrastructure-gpu-compatibility-when-running-gemma-2-with-flashinfer-on-an-nvidia--6f3f1857

Tier 1 · 70%
service_resilience

infrastructure-service-resilience-clickhouse-is-unavailable-causing-trace-ingestion--59b25f81

Tier 1 · 70%
mypy_compatibility

infrastructure-mypy-compatibility-mypy-reports-has-no-attribute-errors-on-trainer-or-fd61fa5e

Tier 1 · 70%
repo_structure

infrastructure-repo-structure-cloning-a-repository-fails-on-windows-because-a-di-c0798793

Tier 1 · 70%
provider_migration

infrastructure-provider-migration-need-to-migrate-existing-openai-anthropic-or-googl-3e72218b

Tier 1 · 70%
streamable_http_race_condition

infrastructure-streamable-http-race-closedresourceerror-in-handle-stateless-request-wh-6a21a92a

Tier 1 · 70%

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics