SII-yangdianandSII-yangdian a4b14b98c6 [Kernel] Speed up silu_and_mul_per_block_quant with warp-shuffle reduction + vectorized I/O (#44173) ...

Signed-off-by: SII-yangdian <yangdian@sii.edu.cn>
Co-authored-by: SII-yangdian <yangdian@sii.edu.cn>

2026-06-09 10:41:26 -07:00

..

fused_layernorm_dynamic_per_token_quant.cu

[7/n] Migrate pos_encoding and norm kernels to libtorch stable ABI (continued) (#43209)

2026-05-23 13:20:00 +08:00

fused_silu_mul_block_quant.cu

[Kernel] Speed up silu_and_mul_per_block_quant with warp-shuffle reduction + vectorized I/O (#44173)

2026-06-09 10:41:26 -07:00

layernorm_utils.cuh

[7/n] Migrate pos_encoding and norm kernels to libtorch stable ABI (continued) (#43209)

2026-05-23 13:20:00 +08:00

quant_conversions.cuh

[7/n] Migrate pos_encoding and norm kernels to libtorch stable ABI (continued) (#43209)

2026-05-23 13:20:00 +08:00