Yineng Zhang 9971dc2283 Revert "feat: Add FlashMLA submodule (#4449)" (#4470)

2025-03-16 01:30:05 -07:00

..

speculative

…

test_activation.py

…

test_awq_dequant.py

Add awq dequantize kernel to sgl with 1x to 3x speedup (#4104)

2025-03-12 00:10:02 -07:00

test_bmm_fp8.py

…

test_cublas_grouped_gemm.py

…

test_deep_gemm.py

…

test_fp8_blockwise_gemm.py

…

test_fp8_gemm.py

…

test_int8_gemm.py

…

test_lightning_attention_decode.py

…

test_moe_align.py

…

test_moe_topk_softmax.py

Add moe topk softmax templated from vllm (#4302)

2025-03-14 12:03:33 -07:00

test_norm.py

…

test_per_tensor_quant_fp8.py

…

test_per_token_group_quant_fp8.py

…

test_per_token_quant_fp8.py

fix accuracy issue (#4376)

2025-03-13 02:06:22 -07:00

test_rotary_embedding.py

Simplify tests & Fix trtllm custom allreduce registration (#4252)

2025-03-10 01:24:22 -07:00

test_sampling.py

…

test_trt_allreduce.py

…