conformance-testing

#conformance-testing

Deterministic LLM Inference Across GPU Kernels: Power-of-Two INT8 Quantization Scales and the Limits of Tolerance-Based Conformance

arXiv cs.LG ↗ · 2026-09-02 Cached

This paper evaluates conformance suites for INT8 quantization in LLM inference, finding that power-of-two scales enable cross-kernel bitwise determinism, while tolerance-based checks are limited to preconditions and boundedness.

0 favorites 0 likes

#conformance-testing

The Integer Alibi: Localizing Cross-Kernel Divergence in INT8-Quantized LLM Inference

arXiv cs.LG ↗ · 2026-08-17 Cached

This paper tests the interchangeability of CUTLASS and Triton INT8 quantized GPU kernels in LLM inference using vLLM, finding divergent outputs due to scale application and rounding, and proposes a conformance procedure for kernel equivalence.

0 favorites 0 likes

conformance-testing

Deterministic LLM Inference Across GPU Kernels: Power-of-Two INT8 Quantization Scales and the Limits of Tolerance-Based Conformance

The Integer Alibi: Localizing Cross-Kernel Divergence in INT8-Quantized LLM Inference

Submit Feedback