# Qwen3.8-27B (RadixArk NVFP4 + DFlash2 on SGLang) — 1× DGX Spark / GB10,
# TP=1.
#
# SGLang + DFlash2 block-diffusion speculative decoding. Per the community
# (MiaAI / forum 380350), DFlash2 on NVFP4 ties DSpark on code and *beats it*
# on prose/essay and short-chat once counted right. This is the fork/engine
# the forum's high tok/s numbers (52-61 code single, 87 TP=2) came from — NOT
# the stock DSpark path.
#
# Image: lmsysorg/sglang:qwen38-27b-dflash2-minoverlay — a locally-built overlay
#   of the 5 DFlash2 modules onto the cookbook qwen38-27b image. The cookbook
#   tag itself predates DFlash2 (upstream merged commit c14312a66 on
#   2026-08-19, after every published tag), so the modules are overlaid.
#   The minoverlay modules already bake in the quantized-head selector fix
#   (should_apply_lm_head_quant_method) so DFLASH runs the NVFP4 lm_head in
#   place — no dense dequant.
#
# Draft: z-lab/Qwen3.8-27B-DFlash2 @ 50307d4 (block-diffusion drafter, 3.6 GB).
#
# Model: RadixArk/Qwen3.8-27B-NVFP4 (modelopt)
#
# PREREQUISITES (on the node):
#   hfrs download RadixArk/Qwen3.8-27B-NVFP4
#   hfrs download z-lab/Qwen3.8-27B-DFlash2
#   docker build the minoverlay image (or use the recipe's docker_image as-is)
#
# REFERENCE:
#   https://github.com/MiaAI-Lab/Qwen3.8-27B-SGLang-DGX-Spark  (start-dflash.sh)
#   https://forums.developer.nvidia.com/t/qwen3-8-27b-on-dual-sparks/380350

engine = "sglang"
name = "Qwen3.8-27B (RadixArk NVFP4, SGLang DFlash2)"
docker_image = "lmsysorg/sglang:qwen38-27b-dflash2-minoverlay"
model = "RadixArk/Qwen3.8-27B-NVFP4"
required_nodes = 1
tensor_parallel_size = 1
pipeline_parallel_size = 1
distributed_backend = "mp"
shm_size = "32gb"

entrypoint = ["python3", "-m", "sglang.launch_server"]

args = [
    # Memory — NVFP4 needs 0.90 (0.95 hard-rebooted the box at graph capture)
    "--mem-fraction-static", "0.90",
    "--max-running-requests", "10",
    "--max-mamba-cache-size", "30",
    # Attention / KV
    "--attention-backend", "flashinfer",
    "--kv-cache-dtype", "fp8_e4m3",
    # Mamba GDN hybrid — DFLASH requires extra_buffer (not extra_buffer_lazy)
    "--mamba-ssm-dtype", "bfloat16",
    "--mamba-full-memory-ratio", "4.21",
    "--mamba-radix-cache-strategy", "extra_buffer",
    # Chunked prefill
    "--chunked-prefill-size", "8192",
    # DFlash2 block-diffusion speculative decoding
    "--speculative-algorithm", "DFLASH",
    "--speculative-draft-model-path", "z-lab/Qwen3.8-27B-DFlash2",
    "--speculative-draft-model-revision", "50307d4c4cde6860d4eee73e2547cd786fe8e8a4",
    "--speculative-num-draft-tokens", "8",
    # Tokenizer / reasoning / tool calling (Qwen3 family)
    "--reasoning-parser", "qwen3",
    "--tool-call-parser", "qwen3_coder",
    # Observability
    "--enable-metrics",
    "--enable-cache-report",
]

[env]
HF_HUB_OFFLINE = "1"
SGLANG_OPT_MAMBA_SKIP_DECODE_LOCK = "1"
TORCH_CUDA_ARCH_LIST = "12.1a"
CUTE_DSL_ARCH = "sm_121a"
OMP_NUM_THREADS = "4"