AIbin bf7e2424d0 [Optimization][Feature]Supports multiple batches of DSK-DSA. (#6930) ...

* support DSA_MUTI_BATCH

* update test topk

* update dsk-dsa

2026-03-20 15:59:22 +08:00

..

cpu_ops

…

gpu_ops

[Optimization][Feature]Supports multiple batches of DSK-DSA. (#6930)

2026-03-20 15:59:22 +08:00

iluvatar_ops

[Iluvatar] Optimize decode group_gemm and Support cuda graph for ernie (#6803)

2026-03-12 19:21:17 +08:00

metax_ops

[Model Runner] Deprecate not_need_stop (#6356)

2026-03-05 10:55:42 +08:00

third_party

…

utils

【Optim】Optimize grid dimensions using max_tokens_per_expert for MoE models (#6007)

2026-01-15 19:18:42 +08:00

xpu_ops

[XPU] use quant2d_per_token for weight quant int8 && fix some XPU Kernel check (#6869)

2026-03-17 19:44:48 +08:00

0001-DeepGEMM-95e81b3.patch

…

MANIFEST.in

…

setup_ops_cpu.py

…

setup_ops.py

[BugFix] Cap nvcc -t threads to avoid compilation failures on high-co… (#6885)

2026-03-17 19:27:45 +08:00