sglang.0.4.8.post1/sglang/sgl-kernel/benchmark
hailin d4330e0746 first commit @ sglang v0.4.8.post1 2025-06-29 14:14:11 +00:00
..
bench_awq_dequant.py first commit @ sglang v0.4.8.post1 2025-06-29 14:14:11 +00:00
bench_cutlass_mla.py first commit @ sglang v0.4.8.post1 2025-06-29 14:14:11 +00:00
bench_fp8_blockwise_gemm.py first commit @ sglang v0.4.8.post1 2025-06-29 14:14:11 +00:00
bench_fp8_gemm.py first commit @ sglang v0.4.8.post1 2025-06-29 14:14:11 +00:00
bench_int8_gemm.py first commit @ sglang v0.4.8.post1 2025-06-29 14:14:11 +00:00
bench_lightning_attention_decode.py first commit @ sglang v0.4.8.post1 2025-06-29 14:14:11 +00:00
bench_moe_align_block_size.py first commit @ sglang v0.4.8.post1 2025-06-29 14:14:11 +00:00
bench_moe_ep_post_reorder.py first commit @ sglang v0.4.8.post1 2025-06-29 14:14:11 +00:00
bench_moe_ep_pre_reorder.py first commit @ sglang v0.4.8.post1 2025-06-29 14:14:11 +00:00
bench_moe_fused_gate.py first commit @ sglang v0.4.8.post1 2025-06-29 14:14:11 +00:00
bench_moe_silu_and_mul.py first commit @ sglang v0.4.8.post1 2025-06-29 14:14:11 +00:00
bench_moe_topk_softmax.py first commit @ sglang v0.4.8.post1 2025-06-29 14:14:11 +00:00
bench_per_tensor_quant_fp8.py first commit @ sglang v0.4.8.post1 2025-06-29 14:14:11 +00:00
bench_per_token_group_quant_8bit.py first commit @ sglang v0.4.8.post1 2025-06-29 14:14:11 +00:00
bench_per_token_quant_fp8.py first commit @ sglang v0.4.8.post1 2025-06-29 14:14:11 +00:00
bench_qserve_w4a8_gemm.py first commit @ sglang v0.4.8.post1 2025-06-29 14:14:11 +00:00