# Qwen3.8-27B (FP8 + DSpark draft) — 1× DGX Spark / GB10 (sm_121), TP=1.
#
# DSpark: a dedicated semi-autoregressive draft model (~2.6 GB, 5 layers,
# block_size 7) proposes blocks of tokens that the full model verifies in one
# weight-read. 3× cheaper per guess than the in-checkpoint MTP head, so it wins
# on edit-heavy / structured workloads (blog: 45-48 t/s edit, 17 t/s free-gen,
# 66 t/s aggregate @ c10 on the FP8 target). DSpark blocks are verifier-rejected,
# so no quality risk.
#
# Target: Qwen/Qwen3.8-27B-FP8 (official FP8 quant, 28.75 GB).
# Draft:  RadixArk/Qwen3.8-27B-DSpark (arch DSparkDraftModel, bf16, 5 layers,
#         dspark_block_size 7). Downloaded via hfrs into the node HF cache.
#
# Image: ghcr.io/timothystewart6/vllm-gb10:v0.27.1-gb10.2
#   vLLM 0.27.1 (installed 0.27.2.dev0+g6e448d0ea), supports method "dspark"
#   (SpeculativeMethod Literal includes dspark) + Qwen3DSparkModel draft.
#
# PREREQUISITES:
#   Target + draft cached on the node (dgx1 ~/.cache/huggingface → NAS):
#       hfrs download Qwen/Qwen3.8-27B-FP8
#       hfrs download RadixArk/Qwen3.8-27B-DSpark
#
# REFERENCE:
#   https://blog.kubesimplify.com/qwen3-8-27b-on-dgx-spark  (DSpark section)
#   https://huggingface.co/RadixArk/Qwen3.8-27B-DSpark
#   https://forums.developer.nvidia.com/t/qwen3-8-27b-on-dual-sparks/380350

engine = "vllm"
name = "Qwen3.8-27B (FP8 + DSpark)"
docker_image = "ghcr.io/timothystewart6/vllm-gb10:v0.27.1-gb10.2"
model = "Qwen/Qwen3.8-27B-FP8"
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", "8192",
    "--gpu-memory-utilization", "0.75",
    "--served-model-name", "qwen3.8-27b",
    # Engine backends (dense GQA — FlashInfer)
    "--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 (not the in-checkpoint
    # MTP head). num_speculative_tokens must equal the draft's block size (7).
    # The draft lives in a local dir (arch-patched copy of RadixArk/Qwen3.8-27B-DSpark
    # re-labelled `Qwen3DSparkModel` so vLLM routes it to qwen3_dspark, not the
    # DeepSeek-V4 DSpark code path) bind-mounted at /dspark-draft below.
    "--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,
# mounted at /dspark-draft so vLLM loads it via the qwen3_dspark draft class.
[[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"