Multiple refactors of DeepSeek V32 and context parallel (#16305)

This commit is contained in:
Baizhou Zhang
2026-01-03 02:21:22 +08:00
committed by GitHub
parent 1cfd2b2ded
commit f07e76b229
7 changed files with 193 additions and 38 deletions
+3 -2
View File
@@ -133,8 +133,9 @@ suites = {
TestFile("test_deepseek_v3_mtp.py", 275),
TestFile("test_disaggregation_hybrid_attention.py", 600),
TestFile("models/test_kimi_k2_models.py", 200),
TestFile("test_deepseek_v32_basic.py", 275),
TestFile("test_deepseek_v32_mtp.py", 275),
TestFile("test_deepseek_v32_basic.py", 360),
TestFile("test_deepseek_v32_mtp.py", 360),
TestFile("test_deepseek_v32_cp_single_node.py", 360),
TestFile("models/test_mimo_models.py", 200),
],
"per-commit-8-gpu-h20": [