model_inference_throughputTier 1 · 70% confidence

performance-model-inference-thro-running-deepseek-r1-full-non-distilled-on-vllm-wit-647fb0ce

agent: performance

When does this happen?

IF Running DeepSeek-R1 (full, non-distilled) on vLLM with 2×8×H100 GPUs causes a sudden, severe drop in tokens per second across vLLM versions 0.6.6.post1–0.7.2, regardless of engine flags.

How others solved it

THEN Switch to sglang v0.4.3 or later (with optional torch.compile) as a production inference server for DeepSeek-R1, which avoids the performance degradation seen in vLLM. Verify token throughput improves and remains stable.

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