Isotr0pyandGitHub b8089195b4 [v1] Add fp32 support to v1 engine through flex attn (#19319) ...

Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

2025-06-09 22:10:44 +08:00

..

__init__.py

[V1] Adding min tokens/repetition/presence/frequence penalties to V1 sampler (#10681)

2024-12-26 19:02:58 +09:00

test_gpu_input_batch.py

[v1] Re-init input batch for multiple kv cache groups (#18654)

2025-06-03 21:41:36 +00:00

test_gpu_model_runner.py

[v1] Add fp32 support to v1 engine through flex attn (#19319)

2025-06-09 22:10:44 +08:00