wangding zeng 5d60def02c DeepseekMoE support with Fused MoE kernel (#2453) ...

Co-authored-by: roy <jasonailu87@gmail.com>

2024-01-29 21:19:48 -08:00

..

conftest.py

Support FP8-E5M2 KV Cache (#2279)

2024-01-28 16:43:54 -08:00

test_activation.py

[FIX] Support non-zero CUDA devices in custom kernels (#1959)

2024-01-02 19:09:59 -08:00

test_attention.py

Support FP8-E5M2 KV Cache (#2279)

2024-01-28 16:43:54 -08:00

test_cache.py

Support FP8-E5M2 KV Cache (#2279)

2024-01-28 16:43:54 -08:00

test_fused_moe.py

DeepseekMoE support with Fused MoE kernel (#2453)

2024-01-29 21:19:48 -08:00

test_layernorm.py

[FIX] Support non-zero CUDA devices in custom kernels (#1959)

2024-01-02 19:09:59 -08:00

test_pos_encoding.py

[FIX] Support non-zero CUDA devices in custom kernels (#1959)

2024-01-02 19:09:59 -08:00

test_prefix_prefill.py

Add a 1-line docstring to explain why calling context_attention_fwd twice in test_prefix_prefill.py (#2553)

2024-01-22 14:47:25 -08:00