Replaced grouped_gemm with vLLM's Fused MoE Kernel for Inference Optimization
#7
| Job | Run time |
|---|---|
| 2m 25s | |
| 2m 25s |
grouped_gemm with vLLM's Fused MoE Kernel for Inference Optimization
#7
| Job | Run time |
|---|---|
| 2m 25s | |
| 2m 25s |