[ROCm][Quantization][5/N] Refactor quark_moe w8a8-int8 w/ oracle (#46765)

Signed-off-by: amd-sourjya <amd-sourjya@users.noreply.github.com>
Co-authored-by: amd-sourjya <amd-sourjya@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
This commit is contained in:
amd-sourjya
2026-07-27 16:01:34 -05:00
committed by GitHub
co-authored by amd-sourjya Cursor Andreas Karatzas
parent b5bcb3ce88
commit 1053e248f0
8 changed files with 234 additions and 17 deletions
+1 -1
View File
@@ -150,7 +150,7 @@ def test_quark_int8_w_per_tensor_a_per_tensor(vllm_runner, tp):
@pytest.mark.parametrize("tp", [1])
def test_quark_int8_w8a8_moe(vllm_runner, tp):
"""Test W8A8 INT8 MoE quantization with a tiny Qwen3 MoE model."""
model_path = "nameistoken/tiny-qwen3-moe-w8a8-int8-quark"
model_path = "amd/tiny-qwen3-moe-w8a8-int8"
with vllm_runner(
model_path,
enforce_eager=True,