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 10, 09:00 UTC
[CI] Allow Deprecated Quantization For LM Eval Tests (#32065)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Micah Williamson committed
Jan 9, 2026 at 20:10 UTC
ac0675ff6b40768293ef4b87741b161f6cf4518b
1 file changed
+1
.buildkite/lm-eval-harness/test_lm_eval_correctness.py
+1
@@ -60,6 +60,7 @@ def launch_lm_eval(eval_config, tp_size):
60
f"add_bos_token=true,"
61
f"trust_remote_code={trust_remote_code},"
62
f"max_model_len={max_model_len},"
63
+ "allow_deprecated_quantization=True,"
64
)
65
66
env_vars = eval_config.get("env_vars", None)