We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 57f5ba5 commit 1778fefCopy full SHA for 1778fef
tests/integration/defs/test_e2e.py
@@ -2208,7 +2208,7 @@ def test_relaxed_acceptance_quickstart_advanced_deepseek_r1_8gpus(
2208
"--moe_ep_size=8",
2209
"--tp_size=8",
2210
"--use_cuda_graph",
2211
- f"--kv_cache_fraction={_MEM_FRACTION_80 if is_blackwell else _MEM_FRACTION_95}",
+ f"--kv_cache_fraction={_MEM_FRACTION_50 if is_blackwell else _MEM_FRACTION_95}",
2212
"--max_batch_size=1",
2213
"--max_seq_len=3000",
2214
"--disable_kv_cache_reuse",
0 commit comments