Tag
The paper proposes a claim-gated auditing specification for generative search to address omissions in source relationships, ensuring complete evidence and disclosure for reliable answer interpretation.
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.
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.