Xiaoyu Zhang 8e09b37077 Sgl kernel fused_moe_gate support n_shared_experts (#5440)

2025-04-17 23:05:15 -07:00

..

speculative

…

test_activation.py

…

test_awq_dequant.py

[Misc] clean up vllm in sgl-kernel test (#5189)

2025-04-09 01:22:13 -07:00

test_bmm_fp8.py

…

test_custom_allreduce.py

sgl-kernel transfer custom allreduce from trt kernel to vllm kernel (#5079)

2025-04-05 14:23:20 -07:00

test_cutlass_mla.py

BLackwell cutlass mla: Add check for bad page size/block num combinations (#5431)

2025-04-15 14:07:42 -07:00

test_flash_attention.py

…

test_fp4_gemm.py

…

test_fp4_quantize.py

…

test_fp8_blockwise_gemm.py

…

test_fp8_gemm.py

…

test_int8_gemm.py

…

test_lightning_attention_decode.py

…

test_merge_state_v2.py

kernel: support slightly faster merge_state_v2 cuda kernel (#5381)

2025-04-14 21:28:23 -07:00

test_merge_state.py

…

test_moe_align.py

…

test_moe_fused_gate.py

…

test_moe_topk_softmax.py

…

test_norm.py

…

test_per_tensor_quant_fp8.py

…

test_per_token_group_quant_8bit.py

…

test_per_token_quant_fp8.py

…

test_rotary_embedding.py

[Misc] Clean sgl-kernel test (#5216)

2025-04-10 11:28:41 -07:00

test_sampling.py

…

test_sparse_flash_attn.py

…