tmp: Increase token count for transfer

kthui · kthui · commit 1abc47fdca09 · 2025-12-15T14:14:05.000-08:00
Signed-off-by: Jacky &lt;18255193+kthui@users.noreply.github.com&gt;
diff --git a/tests/fault_tolerance/cancellation/test_trtllm.py b/tests/fault_tolerance/cancellation/test_trtllm.py
@@ -82,7 +82,7 @@ def __init__(
         if mode != "prefill_and_decode":
             with open("test_request_cancellation_trtllm_config.yaml", "w") as f:
                 f.write(
-                    "cache_transceiver_config:\n  backend: DEFAULT\n  max_tokens_in_buffer: 16384\n"
+                    "cache_transceiver_config:\n  backend: DEFAULT\n  max_tokens_in_buffer: 32767\n"
                 )
                 f.write("disable_overlap_scheduler: true\n")
                 f.write("kv_cache_config:\n  max_tokens: 16384\n")

Original file line number	Diff line number	Diff line change
`@@ -82,7 +82,7 @@ def __init__(`
`82`	`82`	`if mode != "prefill_and_decode":`
`83`	`83`	`with open("test_request_cancellation_trtllm_config.yaml", "w") as f:`
`84`	`84`	`f.write(`
`85`		`- "cache_transceiver_config:\n backend: DEFAULT\n max_tokens_in_buffer: 16384\n"`
	`85`	`+ "cache_transceiver_config:\n backend: DEFAULT\n max_tokens_in_buffer: 32767\n"`
`86`	`86`	`)`
`87`	`87`	`f.write("disable_overlap_scheduler: true\n")`
`88`	`88`	`f.write("kv_cache_config:\n max_tokens: 16384\n")`