A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 11, 21:15 UTC
[MISC]: change NIXL compatibility hash logging level to debug (#30182)
AuruTus committed
Dec 7, 2025 at 08:21 UTC
8d3da4c79ddbd199d4185c505bcf3a5d7e7a3316
1 file changed
+1
-1
vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py
+1
-1
@@ -189,7 +189,7 @@ def compute_nixl_compatibility_hash(
189
}
190
191
compat_hash = hash_factors(factors)
192
- logger.info(
192
+ logger.debug(
193
"NIXL compatibility hash: %s (model=%s, dtype=%s, num_kv_heads=%d, "
194
"cache_dtype=%s, attn_backend=%s)",
195
compat_hash,