[ROCM] Optimized deepseek-r1 model with rmsnorm + fp8 quant fusion (#12689)

should be clean after https://github.com/sgl-project/sglang/pull/13017 landed
2025-11-11 02:59:10 -08:00
parent ea10a9d165
commit 4a78031a71
6 changed files with 331 additions and 22 deletions
@@ -421,6 +421,7 @@ suite_amd = {
        TestFile("openai_server/validation/test_request_length_validation.py", 31),
        TestFile("quant/test_awq_dequant.py", 2),
        TestFile("quant/test_block_int8.py", 22),
+        TestFile("quant/test_fused_rms_fp8_group_quant.py", 10),
        TestFile("rl/test_update_weights_from_disk.py", 210),
        TestFile("test_abort.py", 51),
        TestFile("test_chunked_prefill.py", 410),