chips infrastructure
The Spec Sheet Said INT8. The Stack Said No
An audit traced Blackwell Ultra's default INT8 failure through the ISA, kernel library and two serving engines.
Summary
An audit traced Blackwell Ultra's default INT8 failure through the ISA, kernel library and two serving engines.
The audit begins with a roughly 30-to-one dense-throughput ratio between FP8 and INT8 in published B300 specifications, then follows support through PTX, CUTLASS, vLLM and SGLang. It reports no fifth-generation integer tensor-core path for the target ISA, skipped INT8 kernel generation, a vLLM runtime failure after model load and SGLang kernels that stop at an earlier architecture. A Triton reroute can provide an escape hatch. The finding is about the tested full software stack, not a claim that integer arithmetic is absent from the chip.
Why it matters
An audit traced Blackwell Ultra's default INT8 failure through the ISA, kernel library and two serving engines.
Limits and context
- The finding is about the tested full software stack, not a claim that integer arithmetic is absent from the chip.
Key claims
An audit traced Blackwell Ultra's default INT8 failure through the ISA, kernel library and two serving engines.
Qualification: The finding is about the tested full software stack, not a claim that integer arithmetic is absent from the chip.
Evidence: source-2026-08-13-005
Sources
- arXiv preprint 2608.11693arXiv · primary research
Corrections
No corrections have been recorded for this story.