[Bugfix] serving_llama70B_tp4 benchmark was silently running at tensor_parallel_size=1 (#50766)
Signed-off-by: Turner Jabbour <doubleujabbour@gmail.com> Co-authored-by: Claude <noreply@anthropic.com>
Turner Jabbour committed
Aug 2, 2026 at 20:26 UTC
e42c230e4ff4e3b44b100ced7d731a5190948d2e
1 file changed
+1
.buildkite/performance-benchmarks/tests/serving-tests.json
+1
@@ -76,6 +76,7 @@
76
"test_name": "serving_llama70B_tp4_random_128_128",
77
"server_parameters": {
78
"model": "meta-llama/Llama-3.3-70B-Instruct",
79
+ "tensor_parallel_size": 4,
80
"async_scheduling": "",
81
"no_enable_prefix_caching": "",
82
"max_num_batched_tokens": 8192