Files
worker-vllm/configs/gpt-oss/gpt_oss_120b.yaml
T

10 lines
309 B
YAML

model: openai/gpt-oss-120b
gpu-memory-utilization: 0.95
max-model-len: 8192
dtype: auto
trust-remote-code: true
enforce-eager: false
enable-prefix-caching: true
enable-chunked-prefill: true
speculative-config: '{"model":"RedHatAI/gpt-oss-120b-speculator.eagle3","method":"eagle3","num_speculative_tokens":3}'