Views
No views yet
vllm serve CohereLabs/North-Mini-Code-1.0 \
-tp 2 \
--max-model-len 320000 \
--tool-call-parser cohere_command4 \
--reasoning-parser cohere_command4 \
--enable-auto-tool-choice \
--speculative_config "{\"method\": \"eagle\", \"model\": \"CohereLabs/North-Mini-Code-1.0-eagle\", \"num_speculative_tokens\": 3, \"draft_tensor_parallel_size\": 2}"