From 5816ceabdf2941d2e81872b0dd7c197b5b864b85 Mon Sep 17 00:00:00 2001
From: narmstrong-berry <narmstrong@berri.ai>
Date: Wed, 4 Nov 2026 02:25:20 +0000
Subject: [PATCH] feat(loadtest): stream-1m workload, all-streamed
 near-1M-token bodies at rising rates

---
 .../loadtest/workloads/stream-1m.json         | 24 +++++++++++++++++++
 1 file changed, 24 insertions(+)
 create mode 100644 litellm-rust/loadtest/workloads/stream-1m.json

diff --git a/litellm-rust/loadtest/workloads/stream-1m.json b/litellm-rust/loadtest/workloads/stream-1m.json
new file mode 100644
index 00000000000..0efdd348a8c
--- /dev/null
+++ b/litellm-rust/loadtest/workloads/stream-1m.json
@@ -0,0 +1,24 @@
+{
+  "name": "1M-token streams at rising rates (0.5 to 8 rps, 3 minutes each): parsing CPU, memory per open stream and first-byte time at the largest context",
+  "stages": [
+    {"duration_s": 180, "rps": 0.5},
+    {"duration_s": 180, "rps": 1},
+    {"duration_s": 180, "rps": 2},
+    {"duration_s": 180, "rps": 4},
+    {"duration_s": 180, "rps": 8}
+  ],
+  "nonstream_max_s": 360,
+  "warmup_s": 30,
+  "keys": {"file": "out/keys.txt", "zipf_s": 0},
+  "models": {"chat": {"prefix": "gpt-6-astra-", "count": 10}, "messages": {"prefix": "claude-opus-5-5-", "count": 10}},
+  "classes": [
+    {"name": "stream-1m-messages", "weight": 1, "endpoint": "messages", "stream_fraction": 1,
+     "context_tokens": {"dist": "uniform", "min": 950000, "max": 1000000},
+     "ttft_ms": {"dist": "uniform", "min": 1000, "max": 3000},
+     "duration_s": {"dist": "uniform", "min": 5, "max": 60}},
+    {"name": "stream-1m-chat", "weight": 1, "endpoint": "chat", "stream_fraction": 1,
+     "context_tokens": {"dist": "uniform", "min": 950000, "max": 1000000},
+     "ttft_ms": {"dist": "uniform", "min": 1000, "max": 3000},
+     "duration_s": {"dist": "uniform", "min": 5, "max": 60}}
+  ]
+}