Lianmin Zheng 20315697f4 move all get_stream in sgl_kernel to c++ to reduce the launch overhead (#12521)

2025-11-02 13:15:05 -08:00

..

activation.cu

…

cast.cu

move all get_stream in sgl_kernel to c++ to reduce the launch overhead (#12521)

2025-11-02 13:15:05 -08:00

concat_mla.cu

[Fix] concat_mla_absorb_q_kernel fails for long inputs (#12453)

2025-11-02 11:52:06 -08:00

copy.cu

…

fused_add_rms_norm_kernel.cu

…

pos_enc.cuh

Add PDL support for quant kernel and rope kernel (#9106)

2025-08-20 01:56:29 -07:00

rope.cu

move all get_stream in sgl_kernel to c++ to reduce the launch overhead (#12521)

2025-11-02 13:15:05 -08:00

topk.cu

[DeepseekV32] Add fast_topk_transform_ragged_fused kernel (#11815)

2025-10-19 17:13:39 -07:00

utils.cuh

[sgl-kernel] Optimize concat_mla_k kernel (#10543)

2025-09-28 23:04:22 +08:00