vllm/tests/kernels
2024-01-03 11:30:22 -08:00
..
conftest.py [FIX] Support non-zero CUDA devices in custom kernels (#1959) 2024-01-02 19:09:59 -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 [FIX] Support non-zero CUDA devices in custom kernels (#1959) 2024-01-02 19:09:59 -08:00
test_cache.py Use NCCL instead of ray for control-plane communication to remove serialization overhead (#2221) 2024-01-03 11:30:22 -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