…

..

spatial

…

speculative

…

test_activation.py

…

test_apply_token_bitmask_inplace.py

…

test_awq_dequant.py

…

test_bmm_fp8.py

…

test_causal_conv1d.py

Add mamba kernel (#10234)

2025-09-09 12:58:43 -07:00

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

Disable kernel cutlass_mla_decode on SM103 (#10058)

2025-09-06 01:35:18 -07:00

test_cutlass_w4a8_moe_mm.py

…

test_dsv3_fused_a_gemm.py

…

test_dsv3_router_gemm.py

[Kimi K2] dsv3_router_gemm supports NUM_EXPERTS == 384 (#8013)

2025-08-01 22:01:24 +08:00

test_flash_attention_4.py

…

test_flash_attention.py

…

test_fp4_gemm.py

…

test_fp4_quantize.py

…

test_fp8_blockwise_gemm.py

…

test_fp8_blockwise_moe.py

Update CUTLASS 4.2 & Enable K-Major Scale Factor for SM90 FP8 Blockwise Group GEMM (#9559)

2025-08-24 23:24:43 -07:00

test_fp8_gemm.py

…

test_gptq_kernel.py

…

test_int8_gemm.py

…

test_kvcacheio.py

…

test_lightning_attention_decode.py

…

test_marlin_gemm.py

…

test_marlin_repack.py

…

test_merge_state_v2.py

…

test_merge_state.py

…

test_moe_align.py

…

test_moe_fused_gate.py

…

test_moe_topk_softmax.py

…

test_mscclpp.py

support 1 shot allreduce in 1-node and 2-node using mscclpp (#6277)

2025-06-04 22:11:24 -07:00

test_norm.py

cleanup sgl-kernel kernels (#3175)

2025-01-27 19:11:01 +08:00

test_per_tensor_quant_fp8.py

…

test_per_token_group_quant_8bit.py

…

test_per_token_quant_fp8.py

…

test_qserve_w4a8_per_chn_gemm.py

[1/2] Support Qserve (#6457)

2025-05-21 19:48:59 -07:00

test_qserve_w4a8_per_group_gemm.py

…

test_rotary_embedding.py

…

test_sampling.py

…

test_sparse_flash_attn.py

…

utils.py

…