[New Model][ROCm] Add AMD support for DeepSeek V4 (#40871)

Signed-off-by: ganyi <ygan@amd.com>
Signed-off-by: whx-sjtu <xiaowang990929@gmail.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Signed-off-by: tjtanaavllm <tunjian.tan@amd.com>
Co-authored-by: ganyi <ygan@amd.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaavllm <tunjian.tan@amd.com>
This commit is contained in:
Hexiang Wang
2026-05-05 08:55:37 -07:00
committed by GitHub
co-authored by ganyi tjtanaa tjtanaavllm
parent 2228fe6868
commit 628c436301
22 changed files with 939 additions and 134 deletions
+4 -2
View File
@@ -70,7 +70,8 @@ def test_sqrtsoftplus_bias_uses_deepseek_v4_routing_method():
@pytest.mark.skipif(
not current_platform.is_cuda(), reason="This test is skipped on non-CUDA platform."
not current_platform.is_cuda_alike(),
reason="This test is skipped on non-CUDA platform.",
)
@pytest.mark.parametrize("num_tokens", [1, 33, 128])
@pytest.mark.parametrize("hidden_size", [1024, 2048])
@@ -125,7 +126,8 @@ def test_fused_topk_softplus_sqrt(
@pytest.mark.skipif(
not current_platform.is_cuda(), reason="This test is skipped on non-CUDA platform."
not current_platform.is_cuda_alike(),
reason="This test is skipped on non-CUDA platform.",
)
@pytest.mark.parametrize("num_tokens", [1, 33, 128])
@pytest.mark.parametrize("hidden_size", [1024, 2048])