67 lines
2.0 KiB
YAML
67 lines
2.0 KiB
YAML
# Recipe: GLM-4.7-Flash-AWQ-4bit
|
|
# cyankiwi's AWQ quantized GLM-4.7-Flash model
|
|
# Requires a patch for inference speed optimization
|
|
#
|
|
# NOTE: vLLM implementation is suboptimal even with the patch.
|
|
# The model performance is still significantly slower than it should be
|
|
# for a model with this number of active parameters. Running in cluster
|
|
# increases prompt processing performance, but not token generation.
|
|
# Expect ~40 t/s generation speed in both single node and cluster.
|
|
|
|
recipe_version: "1"
|
|
name: GLM-4.7-Flash-AWQ
|
|
description: vLLM serving cyankiwi/GLM-4.7-Flash-AWQ-4bit with speed optimization patch
|
|
|
|
# HuggingFace model to download
|
|
model: cyankiwi/GLM-4.7-Flash-AWQ-4bit
|
|
|
|
# This model can run on single node (solo) or cluster
|
|
cluster_only: false
|
|
|
|
solo_only: false
|
|
|
|
# Container image to use
|
|
container: vllm-node-tf5
|
|
|
|
# Build arguments for build-and-copy.sh
|
|
# tf5 = transformers 5.0 (required for GLM-4.7)
|
|
build_args:
|
|
- --pre-tf
|
|
|
|
# Mods to apply before running (paths relative to repo root)
|
|
# This mod prevents severe inference speed degradation
|
|
mods:
|
|
- mods/fix-glm-4.7-flash-AWQ
|
|
|
|
# Default settings (can be overridden via CLI)
|
|
defaults:
|
|
port: 8000
|
|
host: 0.0.0.0
|
|
tensor_parallel: 1
|
|
gpu_memory_utilization: 0.7
|
|
max_model_len: 202752
|
|
max_num_batched_tokens: 4096
|
|
max_num_seqs: 64
|
|
served_model_name: glm-4.7-flash
|
|
|
|
# Environment variables to set in the container
|
|
env:
|
|
# Add any required env vars here
|
|
|
|
# The vLLM serve command template
|
|
# Use {var_name} for substitution from defaults/overrides
|
|
# In cluster mode, --distributed-executor-backend ray and -tp 2 are added
|
|
command: |
|
|
vllm serve cyankiwi/GLM-4.7-Flash-AWQ-4bit \
|
|
--tool-call-parser glm47 \
|
|
--reasoning-parser glm45 \
|
|
--enable-auto-tool-choice \
|
|
--served-model-name {served_model_name} \
|
|
--max-model-len {max_model_len} \
|
|
--max-num-batched-tokens {max_num_batched_tokens} \
|
|
--max-num-seqs {max_num_seqs} \
|
|
--gpu-memory-utilization {gpu_memory_utilization} \
|
|
-tp {tensor_parallel} \
|
|
--host {host} \
|
|
--port {port}
|