A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[Bugfix] Fix benchmark_moe.py (#23177)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Jee Jee Li committed
Aug 19, 2025 at 21:39 UTC
4d9c61993ac4209c97b3afef237b2387f2cd9b97
1 file changed
-1
benchmarks/kernels/benchmark_moe.py
-1
@@ -430,7 +430,6 @@ class BenchmarkWorker:
430
hidden_size,
431
topk,
432
dtype_str,
433
- is_marlin=False,
433
)
434
else:
435
config = op_config[min(op_config.keys(), key=lambda x: abs(x - num_tokens))]