Canlin Guo 412bf42a75 [Refactor] Unify _talker_mtp_forward across GPU and NPU model runners (#3476) ...

Signed-off-by: gcanlin <canlinguosdu@gmail.com>

2026-05-31 07:58:00 +08:00

..

cuda

[Blackwell][1/N] Add SageAttention3 diffusion backend on blackwell(GB200/B200/RTX5090/PRO6000/DGX Spark available) (#3015)

2026-05-28 14:08:45 +00:00

musa

[Diffusion][Attention] Support per-role attention backend via CLI (#2681)

2026-05-10 11:59:05 +08:00

npu

[Refactor] Unify _talker_mtp_forward across GPU and NPU model runners (#3476)

2026-05-31 07:58:00 +08:00

rocm

[ROCm] Add support for AITER GroupNorm (#3419)

2026-05-27 11:33:17 +00:00

xpu

[XPU] set flash_attn as default diffusion attn backend and fix k_len for cross_attn (#3525)

2026-05-18 23:58:15 +00:00

__init__.py

[Feat] Add MUSA platform support for Moore Threads GPUs (#2337)

2026-04-01 17:55:00 +08:00

interface.py

[Refactor] Unify _talker_mtp_forward across GPU and NPU model runners (#3476)

2026-05-31 07:58:00 +08:00