# Qwen3.8-27B (Pilcothink Int4 AutoRound + MTP) — 1× DGX Spark / GB10 (sm_121),
# TP=1.
#
# Mixed 4-bit AutoRound quant (20 GB) tuned for a single DGX Spark. Sensitive
# layers kept FP8/FP16; vision layers unquantized. MTP quantized + included.
# Dense 27B, GQA, hybrid DeltaNet+Attention. Text + vision. The community has
# heavily tuned vLLM flags for this exact build (thread 380248 post #39).
#
# 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 the qwen3_5 arch + MTP.
#
# Model: Pilcothink/Qwen3.8-27B-MixedInt4-AutoRound
#   https://huggingface.co/Pilcothink/Qwen3.8-27B-MixedInt4-AutoRound
#
# PREREQUISITES:
#   Weights cached on every node (dgx1 ~/.cache/huggingface → NAS):
#       huggingface-cli download Pilcothink/Qwen3.8-27B-MixedInt4-AutoRound
#
# REFERENCE:
#   https://forums.developer.nvidia.com/t/qwen3-8-27b-mixedint4-autoround-optimized-for-a-single-dgx-spark/380248

engine = "vllm"
name = "Qwen3.8-27B (Int4 AutoRound)"
docker_image = "ghcr.io/timothystewart6/vllm-gb10:v0.27.1-gb10.2"
model = "Pilcothink/Qwen3.8-27B-MixedInt4-AutoRound"
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 (AutoRound community tuning)
    "--optimization-level", "3",
    "--performance-mode", "throughput",
    # Chunked prefill + prefix caching
    "--enable-chunked-prefill",
    "--enable-prefix-caching",
    "--enable-flashinfer-autotune",
    # MTP speculative decoding (quantized draft)
    "--speculative-config", """
'{"method":"mtp","num_speculative_tokens":4}'""",
    # 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",
]

[env]
# AutoRound community tuning (thread 380248 post #39): faster load + higher
# compile level for the 4-bit kernels.
VLLM_TORCH_COMPILE_LEVEL = "3"
VLLM_TRITON_COMPILE_ON_LOAD = "1"
VLLM_WARMUP_BEFORE_SERVING = "1"
VLLM_SKIP_WARMUP = "false"
TORCH_MATMUL_PRECISION = "high"
NVIDIA_FORWARD_COMPAT = "1"
NVIDIA_DISABLE_REQUIRE = "1"
CUDA_DEVICE_MAX_CONNECTIONS = "1"
VLLM_MARLIN_USE_ATOMIC_ADD = "1"
FLASHINFER_DISABLE_VERSION_CHECK = "1"

# Offline mode
HF_HUB_OFFLINE = "1"

# Architecture
TORCH_CUDA_ARCH_LIST = "12.1a"
CUTE_DSL_ARCH = "sm_121a"
OMP_NUM_THREADS = "4"

# GPU memory management
PYTORCH_CUDA_ALLOC_CONF = "expandable_segments:True"

# GPU device isolation
CUDA_VISIBLE_DEVICES = "0"
CUDA_DEVICE_ORDER = "PCI_BUS_ID"
CUDA_CACHE_MAXSIZE = "4294967296"