# baseline.muh — Competition vllm launch configuration
#
# This file stores ONLY the vllm server launch config.
# Kernel tuning values live in muh/include/muh/tuning/tuning_*.cuh
# as constexpr structs — NOT here.
#
# Pipeline:
#   muh/tuning/*.cuh (bi100_* values) → gen_patch.py → vllm kernel patches
#   baseline.muh (vllm config)        → gen_yaml.py → computility-run.yaml

# --- vllm launch configuration ---
vllm:
  model_path: /model
  served_model_name: llm
  max_model_len: 100000
  gpu_memory_utilization: 0.9
  tensor_parallel: 4
  max_num_seqs: 1
  max_num_batched_tokens: 8192
  max_seq_len_to_capture: 32768
  trust_remote_code: true
  disable_log_requests: true
  disable_frontend_multiprocessing: true
  enable_chunked_prefill: true
  enable_auto_tool_choice: true
  tool_call_parser: qwen3_coder
  reasoning_parser: qwen3
  enable_prefix_caching: true

concurrency: 1

env:
  VLLM_ENGINE_ITERATION_TIMEOUT_S: 3600