48 lines
1.2 KiB
YAML
48 lines
1.2 KiB
YAML
# Recipe: Qwen/Qwen3.5-35B-A3B-FP8
|
|
# Qwen/Qwen3.5-35B-A3B model in native FP8 format
|
|
|
|
|
|
recipe_version: "1"
|
|
name: Qwen35-35B-A3B
|
|
description: vLLM serving Qwen3.5-35B-A3B-FP8
|
|
|
|
# HuggingFace model to download (optional, for --download-model)
|
|
model: Qwen/Qwen3.5-35B-A3B-FP8
|
|
|
|
#solo_only: true
|
|
|
|
# Container image to use
|
|
container: vllm-node
|
|
|
|
# Mod required to fix slowness and crash in the cluster (tracking https://github.com/vllm-project/vllm/issues/33857)
|
|
mods:
|
|
- mods/fix-qwen3-coder-next
|
|
|
|
# Default settings (can be overridden via CLI)
|
|
defaults:
|
|
port: 8000
|
|
host: 0.0.0.0
|
|
tensor_parallel: 2
|
|
gpu_memory_utilization: 0.7
|
|
max_model_len: 131072
|
|
|
|
# Environment variables
|
|
env: {}
|
|
|
|
# The vLLM serve command template
|
|
command: |
|
|
vllm serve Qwen/Qwen3.5-35B-A3B-FP8 \
|
|
--max-num-batched-tokens 16384 \
|
|
--enable-auto-tool-choice \
|
|
--tool-call-parser qwen3_coder \
|
|
--gpu-memory-utilization {gpu_memory_utilization} \
|
|
--host {host} \
|
|
--port {port} \
|
|
--kv-cache-dtype fp8 \
|
|
--load-format fastsafetensors \
|
|
--attention-backend flashinfer \
|
|
--enable-prefix-caching \
|
|
--max-model-len {max_model_len} \
|
|
-tp {tensor_parallel} \
|
|
--distributed-executor-backend ray
|