Vanka0051 a963ca3d0b

Merge branch 'main' into perf/gumbel_softmax_sampler

2025-11-07 15:32:22 +08:00

..

__init__.py

feat: achieve inference acceleration for the gpt2 stage

2025-10-24 08:15:00 +00:00

accel_engine.py

Merge branch 'main' into perf/gumbel_softmax_sampler

2025-11-07 15:32:22 +08:00

attention.py

feat: achieve inference acceleration for the gpt2 stage

2025-10-24 08:15:00 +00:00

gpt2_accel.py

feat: achieve inference acceleration for the gpt2 stage

2025-10-24 08:15:00 +00:00

kv_manager.py

feat: achieve inference acceleration for the gpt2 stage

2025-10-24 08:15:00 +00:00