Figure 7a reports forward-plus-backward attention throughput on H100 80GB SXM5; PyTorch is marked OOM at sequence length 16k. The panel covers non-causal attention with head dimension 64.

openai/gpt-5.6-sol

d019b7a37a

The paper used an H100 80GB SXM5; L4 measurements cannot verify the reported H100 335/338 TFLOPs/s values or hardware utilization. · The contract-fixed FlashAttention-2 source identifies as package 2.8.4 and postdates the paper. Its assigned CUDA kernels were unchanged, but an evaluation-only host dispatch was bounded to FP16 head dimensions 64/128 and rejected unassigned SplitKV paths. · The paper does not identify the original FlashAttention package version. The retained official v1.0.9 is only a source-grounded candidate and cannot execute d=128 backward on SM89, leaving 12 assigned comparison values unavailable. · PyTorch d=64 8k non-causal and causal backward exceeded the L4 memory capacity, leaving two assigned values unavailable; isolated fresh-process retries confirmed this was not allocator fragmentation. · The four PyTorch 16k figure positions have no numeric measurement IDs in the fixed contract and were retained as not-assigned rather than benchmarked. · Unresolved measurements: fig7a-8k-pytorch: The preserved parser evidence did not contain a trustworthy metric: JSON 指针没有指向有限数值; fig7b-512-flashattention: The preserved parser evidence did not contain a trustworthy metric: JSON 指针没有指向有限数值; fig7b-1k-flashattention: The preserved parser evidence did not contain a trustworthy metric: JSON 指针没有指向有限数值; fig7b-2k-flashattention: The preserved parser evidence did not contain a trustworthy metric: JSON 指针没有指向有限数值; fig7b-4k-flashattention: The preserved parser evidence did not contain a trustworthy metric: JSON 指针没有指向有限数值; fig7b-8k-flashattention: The preserved parser evidence did not contain a trustworthy metric: JSON 指针没有指向有限数值; fig7b-16k-flashattention: The preserved parser evidence did not contain a trustworthy metric: JSON 指针没有指向有限数值; fig7c-8k-pytorch: The preserved parser evidence did not contain a trustworthy metric: JSON 指针没有指向有限数值; fig7d-512-flashattention: The preserved parser evidence did not contain a trustworthy metric: JSON 指针没有指向有限数值; fig7d-1k-flashattention: The preserved parser evidence did not contain a trustworthy metric: JSON 指针没有指向有限数值; fig7d-2k-flashattention: The preserved parser evidence did not contain a trustworthy metric: JSON 指针没有指向有限数值; fig7d-4k-flashattention: The preserved parser evidence did not contain a trustworthy metric: JSON 指针没有指向有限数值; fig7d-8k-flashattention: The preserved parser evidence did not contain a trustworthy metric: JSON 指针没有指向有限数值; fig7d-16k-flashattention: The preserved parser evidence did not contain a trustworthy metric: JSON 指针没有指向有限数值 · Execution used a roughly 23GB NVIDIA L4 instead of an H100 80GB SXM5, materially affecting throughput and memory behavior. · PyTorch at 16k—the claim's central OOM observation—was not run; it was skipped based on the paper label. · The listed measurements omit a numeric PyTorch 8k result because that L4 attempt OOMed; this does not establish H100 behavior. · The paper does not identify the exact FlashAttention baseline version; v1.0.9 was only a candidate. · The evaluated FlashAttention-2 source identifies as later package 2.8.4 and used a bounded evaluation-only host dispatch. · The inherited 16k-total-token and hidden-dimension-2048 grid remains an assumption because the H100 paragraph does not independently restate it. · The captured run freshly measured the listed Figure 7a cells with 30 forward and 30 backward CUDA-event samples, but on an NVIDIA L4 rather than the claimed H100 80GB SXM5. Since throughput is device-dependent, these absolute values are not comparable to Figure 7a. The central qualitative claim that PyTorch is OOM at 16k was not executed: the evaluator skipped PyTorch 16k and labeled it not_assigned based on the paper. The run therefore establishes only L4 portability behavior, not the H100 throughput or OOM claim. Some original claim measurements remain without evidence; available measurements are assessed individually.