|
|
@@ -58,7 +58,7 @@ args = [
|
|
|
"--gpu-memory-utilization", "0.85",
|
|
|
"--kv-cache-memory-bytes", "17179869184",
|
|
|
"--speculative-config", """
|
|
|
-'{"method":"dflash","model":"local-inference-lab/GLM-5.3-Flash-DFlash2","num_speculative_tokens":7}'""",
|
|
|
+'{"method":"dflash","model":"local-inference-lab/GLM-5.3-Flash-DFlash2-bf16","num_speculative_tokens":7}'""",
|
|
|
"--language-model-only",
|
|
|
# image requests need the mm template shipped/in-wallpaper on aiden's rigs:
|
|
|
# "--chat-template", "<path-to>/chat_template_mm.jinja",
|
