RedHatAI
/

Qwen3-14B-speculator.eagle3

Text Generation

Model card Files Files and versions

alexmarques commited on Dec 2, 2025

Commit

dd06971

·

verified ·

1 Parent(s): 21a51d1

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -147,7 +147,8 @@ vllm serve Qwen/Qwen3-14B \
 GUIDELLM__PREFERRED_ROUTE="chat_completions" \
 guidellm benchmark \
   --target "http://localhost:8000/v1" \
-  --data "RedHatAI/SpeculativeDecoding" \
   --rate-type sweep \
   --max-seconds 600 \
   --output-path "Qwen3-14B-HumanEval.json" \

 GUIDELLM__PREFERRED_ROUTE="chat_completions" \
 guidellm benchmark \
   --target "http://localhost:8000/v1" \
+  --data "RedHatAI/speculator_benchmarks" \
+  --data-args '{"data_files": "HumanEval.jsonl"}' \
   --rate-type sweep \
   --max-seconds 600 \
   --output-path "Qwen3-14B-HumanEval.json" \