Trevor Morris e9f8e42318 Support FP4 gemm (1/2) (#3899)

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

..

speculative

Add greedy verification kernel (#4383)

2025-03-16 00:58:26 -07:00

test_activation.py

…

test_awq_dequant.py

[1/3] fix dsv3 awq issue (#4556)

2025-03-22 01:07:17 -07:00

test_bmm_fp8.py

feat: integrate bmm_fp8 kernel into sgl-kernel (#3056)

2025-01-23 00:39:38 +08:00

test_cublas_grouped_gemm.py

…

test_deep_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

Support serving DeepSeek-R1-Channel-INT8 with 32 L40S. (#4418)

2025-03-17 00:03:43 -07:00

test_lightning_attention_decode.py

…

test_moe_align.py

…

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

…