SemiAnalysis says the comparison uses SGLang, which it describes as a widely used production LLM engine.
SemiAnalysis claims Nvidia Rubin delivers 4.23 times the inference performance per dollar of GB300 NVL72 on SGLang, an LLM engine it describes as widely used in production.
7K
3 Sources, first seen ago
—
Not ranked yet
—
Not ranked yet
@SemiAnalysis_ALERT🚨: NVIDIA SGLANG INFERENCE RUBIN IS 4.23x BETTER 🚀 PERF PER DOLLAR THAN EVEN GB300 NVL72. This is on the widely used production LLM engine called @sgl_project. (1/2)🧵
@sgl_projectQwen3.8 Flash Next on Vera Rubin with NVIDIA Dynamo + SGLang: Up to 6.6× throughput per chip and up to 76% lower modeled cost per total token vs. GB300, at matched per-user speed. Thanks @NVIDIAAI for the partnership and early access, and @SemiAnalysis_ for the results!
@NVIDIAAIRT @sgl_project: Qwen3.8 Flash Next on Vera Rubin with NVIDIA Dynamo + SGLang: Up to 6.6× throughput per chip and up to 76% lower modeled…@SemiAnalysis_ALERT🚨: NVIDIA SGLANG INFERENCE RUBIN IS 4.23x BETTER 🚀 PERF PER DOLLAR THAN EVEN GB300 NVL72. This is on the widely used production LLM engine called @sgl_project. (1/2)🧵@sgl_projectQwen3.8 Flash Next on Vera Rubin with NVIDIA Dynamo + SGLang: Up to 6.6× throughput per chip and up to 76% lower modeled cost per total token vs. GB300, at matched per-user speed. Thanks @NVIDIAAI for the partnership and early access, and @SemiAnalysis_ for the results!@NVIDIAAIRT @sgl_project: Qwen3.8 Flash Next on Vera Rubin with NVIDIA Dynamo + SGLang: Up to 6.6× throughput per chip and up to 76% lower modeled…@SemiAnalysis_ALERT🚨: NVIDIA SGLANG INFERENCE RUBIN IS 4.23x BETTER 🚀 PERF PER DOLLAR THAN EVEN GB300 NVL72. This is on the widely used production LLM engine called @sgl_project. (1/2)🧵@sgl_projectQwen3.8 Flash Next on Vera Rubin with NVIDIA Dynamo + SGLang: Up to 6.6× throughput per chip and up to 76% lower modeled cost per total token vs. GB300, at matched per-user speed. Thanks @NVIDIAAI for the partnership and early access, and @SemiAnalysis_ for the results!@NVIDIAAIRT @sgl_project: Qwen3.8 Flash Next on Vera Rubin with NVIDIA Dynamo + SGLang: Up to 6.6× throughput per chip and up to 76% lower modeled…@SemiAnalysis_ALERT🚨: NVIDIA SGLANG INFERENCE RUBIN IS 4.23x BETTER 🚀 PERF PER DOLLAR THAN EVEN GB300 NVL72. This is on the widely used production LLM engine called @sgl_project. (1/2)🧵@sgl_projectQwen3.8 Flash Next on Vera Rubin with NVIDIA Dynamo + SGLang: Up to 6.6× throughput per chip and up to 76% lower modeled cost per total token vs. GB300, at matched per-user speed. Thanks @NVIDIAAI for the partnership and early access, and @SemiAnalysis_ for the results!@NVIDIAAIRT @sgl_project: Qwen3.8 Flash Next on Vera Rubin with NVIDIA Dynamo + SGLang: Up to 6.6× throughput per chip and up to 76% lower modeled…
