# Gepard-1.0: single-stage native-AR FSQ/NanoCodec TTS (~0.5B).
# Target 1x L4 24GB. Zero-shot only; enforce_eager until the perf PR.
#
# The pipeline pin is required, not cosmetic: the checkpoint's config.json
# self-identifies as qwen3_5_text, so model_type inference cannot reach the
# gepard registry entry, and the architectures fallback would match
# Qwen3_5ForCausalLM against the diffusion pipeline.
pipeline: gepard
async_chunk: false
dtype: bfloat16
trust_remote_code: true

stages:
  - stage_id: 0
    max_num_seqs: 4
    gpu_memory_utilization: 0.3      # AR LM + NanoCodec fit in ~2 GiB
    enforce_eager: true
    enable_prefix_caching: false
    async_scheduling: true
    max_num_batched_tokens: 4096
    max_model_len: 4096
    devices: "0"
    # Override architectures so vLLM resolves our talker rather than the native
    # Qwen3.5 text model. Do NOT override model_type: the backbone's own
    # model_type check needs it to stay qwen3_5_text.
    hf_overrides:
      architectures: ["GepardTalkerForConditionalGeneration"]
    default_sampling_params:
      # All 32 heads are sampled in-model, so vLLM's sampler is pinned
      # deterministic and just argmaxes what forward chose.
      temperature: 0.0
      top_p: 1.0
      top_k: -1
      # One output token is one frame, so this is the frame budget: 1000 frames
      # is ~46 s at 21.5 fps. A backstop, not a target -- normal utterances are
      # 40-420 frames -- but a load-bearing one, because this checkpoint's stop
      # head does not fire on every batched trajectory.
      max_tokens: 1000
      seed: 42
      detokenize: false