# Qwen3.8-27B (unsloth NVFP4 + DSpark) — 1× DGX Spark / GB10 (sm_121), TP=1.
#
# NVFP4 compressed-tensors quant (22 GB) with a dedicated DSpark draft model
# (RadixArk, 2.6 GB, block_size 7) for speculative decoding. Dense 27B, GQA,
# hybrid DeltaNet+Attention. Text + vision. Unsloth Dynamic V3.0 (preview)
# quant — SOTA quality for NVFP4. vLLM-only (lm_head FP8).
#
# DSpark vs the in-checkpoint MTP head (qwen38-27b-nvfp4-unsloth recipe): the
# draft is 3× cheaper per guess and edits/rewrites much faster, at the cost of
# a 2.6 GB draft + a local arch-patched copy. Benchmark both.
#
# Image: ghcr.io/timothystewart6/vllm-gb10:v0.27.1-gb10.2
#   vLLM 0.27.1, torch 2.13+cuda130, FlashInfer built from source,
#   instanttensor. Stock vLLM — supports qwen3_5 arch + method "dspark".
#
# Model: unsloth/Qwen3.8-27B-NVFP4
#   https://huggingface.co/unsloth/Qwen3.8-27B-NVFP4
#
# PREREQUISITES:
#   Weights cached on every node (dgx1 ~/.cache/huggingface → NAS):
#       huggingface-cli download unsloth/Qwen3.8-27B-NVFP4
#       hfrs download RadixArk/Qwen3.8-27B-DSpark  (then cp -aL + patch arch → /home/kilork/dspark-draft)
#
# REFERENCE:
#   https://blog.kubesimplify.com/qwen3-8-27b-on-dgx-spark  (DSpark section)

engine = "vllm"
name = "Qwen3.8-27B (NVFP4 unsloth + DSpark)"
docker_image = "ghcr.io/timothystewart6/vllm-gb10:v0.27.1-gb10.2"
model = "unsloth/Qwen3.8-27B-NVFP4"
parent_model = "Qwen/Qwen3.8-27B"
required_nodes = 1
tensor_parallel_size = 1
pipeline_parallel_size = 1
distributed_backend = "mp"
shm_size = "32gb"

entrypoint = ["vllm", "serve"]

args = [
    # KV cache & memory
    "--kv-cache-dtype", "fp8",
    "--max-model-len", "262144",
    "--max-num-seqs", "6",
    "--max-num-batched-tokens", "16384",
    "--gpu-memory-utilization", "0.75",
    "--served-model-name", "qwen3.8-27b",
    # Engine backends (dense GQA — FlashInfer; NVFP4 route via compressed-tensors)
    "--attention-backend", "flashinfer",
    # Compilation / perf
    "--optimization-level", "3",
    "--performance-mode", "throughput",
    # Chunked prefill + prefix caching
    "--enable-chunked-prefill",
    "--enable-prefix-caching",
    "--enable-flashinfer-autotune",
    # DSpark speculative decoding — dedicated draft model (arch-patched local
    # copy of RadixArk/Qwen3.8-27B-DSpark, re-labelled `Qwen3DSparkModel` so
    # vLLM routes it to qwen3_dspark not the DeepSeek-V4 path). block_size 7.
    # batched-tokens raised to 16384 to fit the draft token slots (warn:
    # max_num_scheduled_tokens=8156 at 8192).
    "--speculative-config", """
'{"method":"dspark","model":"/dspark-draft","num_speculative_tokens":7}'""",
    # Tokenizer / reasoning (Qwen3 family)
    "--tool-call-parser", "qwen3_xml",
    "--reasoning-parser", "qwen3",
    "--enable-auto-tool-choice",
    "--generation-config", "auto",
    "--default-chat-template-kwargs.preserve_thinking=true",
    # Proven generation defaults (thinking mode; Qwen3.8 model-card best
    # practices)
    "--override-generation-config", """
'{"temperature":1.0,"top_p":0.95,"top_k":20,"min_p":0.0,"presence_penalty":0.0,"repetition_penalty":1.0}'""",
    "--trust-remote-code",
]

# DSpark draft model — arch-patched local copy of RadixArk/Qwen3.8-27B-DSpark.
[[extra_mounts]]
host = "/home/kilork/dspark-draft"
container = "/dspark-draft"


[env]
HF_HUB_OFFLINE = "1"
TORCH_CUDA_ARCH_LIST = "12.1a"
CUTE_DSL_ARCH = "sm_121a"
OMP_NUM_THREADS = "4"
PYTORCH_CUDA_ALLOC_CONF = "expandable_segments:True"
CUDA_VISIBLE_DEVICES = "0"
CUDA_DEVICE_ORDER = "PCI_BUS_ID"
CUDA_CACHE_MAXSIZE = "4294967296"