Qingquan Song 45dcfc2e76 Add deepseek style fused moe group gate selection kernel (#4530)

2025-03-29 11:51:45 -07:00

..

speculative

…

test_activation.py

sync flashinfer and update sgl-kernel tests (#3081)

2025-01-23 21:13:55 +08:00

test_awq_dequant.py

…

test_bmm_fp8.py

…

test_cublas_grouped_gemm.py

…

test_fp4_gemm.py

Support FP4 gemm (1/2) (#3899)

2025-03-24 19:50:23 -07:00

test_fp4_quantize.py

Support FP4 gemm (1/2) (#3899)

2025-03-24 19:50:23 -07:00

test_fp8_blockwise_gemm.py

…

test_fp8_gemm.py

…

test_int8_gemm.py

…

test_lightning_attention_decode.py

[Fix] use torch.cat instead of torch.concat to prevent entering the Autograd backends. (#4466)

2025-03-16 00:02:47 -07:00

test_moe_align.py

…

test_moe_fused_gate.py

Add deepseek style fused moe group gate selection kernel (#4530)

2025-03-29 11:51:45 -07:00

test_moe_topk_softmax.py

…

test_norm.py

…

test_per_tensor_quant_fp8.py

…

test_per_token_group_quant_8bit.py

[Quant Kernel] refactored per token group quant fp8 to support int8 up-to 2x faster (#4396)

2025-03-23 23:44:17 -07:00

test_per_token_quant_fp8.py

…

test_rotary_embedding.py

…

test_sampling.py

…

test_trt_allreduce.py

…