Ctrl+K
- bench_in_batch_prefix
- benchmark_vllm_060
- blog_v0_2
- deepseek_v3
- dspy
- generative_agents
- gsm8k
- hellaswag
- json_decode_regex
- json_jump_forward
- json_schema
- kernels
- line_retrieval
- llava_bench
- llm_judge
- long_json_decode
- lora
- mmlu
- mtbench
- multi_chain_reasoning
- multi_document_qa
- multi_turn_chat
- react
- tip_suggestion
- tree_of_thought_deep
- tree_of_thought_v0