Search results

Add MoE (expert-routing) operators — torch.compile structurally can't optimize them (gfx1151 data)

Status: Open.

#156 In ScalingIntelligence/KernelBench;

· fxp opened on Jun 11, 2026

AMD gfx1151 (Strix Halo / RDNA3.5) ROCm results + a precision-downgrade reward-hack case for kernel_static_checker

Status: Open.

#155 In ScalingIntelligence/KernelBench;

· fxp opened on Jun 10, 2026

[BUG] precision cast in _process_input_tensor breaks integer target tensors (cross_entropy / nll_loss / kl_div)

Status: Open.

#151 In ScalingIntelligence/KernelBench;

· moria97 opened on Apr 16, 2026

Does KernelBench has plan to support NCU profiling for kernel evaluation?

Status: Open.

#150 In ScalingIntelligence/KernelBench;

· zigzagcai opened on Apr 9, 2026

Does KernelBench support benchmarking of multiple input shapes?

Status: Open.

#148 In ScalingIntelligence/KernelBench;

· zigzagcai opened on Mar 30, 2026

[BUG] L2/98 Fused Triton Kernel Crashes with double free or corruption / malloc(): invalid next size

Status: Open.

#147 In ScalingIntelligence/KernelBench;

· wuyii8941 opened on Mar 26, 2026

[Discussion/Feature] OOM on 24GB Consumer GPUs (e.g., RTX 4090) during Correctness Check due to massive hardcoded dimensions

Status: Open.

#146 In ScalingIntelligence/KernelBench;

· dunzane opened on Mar 23, 2026

Feature Request: Open Leaderboard

Status: Open.

#141 In ScalingIntelligence/KernelBench;

· jaygala223 opened on Feb 26, 2026

Allow GPU spec prompt configuration

Status: Open.

#122 In ScalingIntelligence/KernelBench;

· jiito opened on Jan 12, 2026

Fix hackable case

Status: Open.

#116 In ScalingIntelligence/KernelBench;

· li-plus opened on Jan 6, 2026

Max Perf / Speedup Modeling

Status: Open.

#115 In ScalingIntelligence/KernelBench;

· simonguozirui opened on Dec 31, 2025

Integrate kernel-level power usage data

Status: Open.

#103 In ScalingIntelligence/KernelBench;

· tanish111 opened on Dec 4, 2025