ATC/atc-GPU
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add GPU Lab configs, docs, and runbooks for VM303.

Browse Source 
Mirror gpu-lab compose files and model-manager catalog from GPU-Dev; document Dockhand mapping and SGLang cutover target.
This commit is contained in:
mo
2026-06-04 02:24:57 +02:00
parent 26aec9ed04
commit c154c94c6d
14 changed files with 930 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
config/model-manager/catalog.json
+515
View File
@@ -0,0 +1,515 @@
{
"models": [
{
"id": "llama3-70b-gptq",
"name": "Llama 3 70B GPTQ",
"description": "Meta Llama 3 open weights. Strong general coder (lab default). 4\u00d7 V100.",
"tags": [
"coding",
"opensource",
"v100_ready"
],
"license": "Llama 3 Community License",
"repo_id": null,
"local_path": "/root/models/llama3-70b-quantized",
"served_name": "llama3-70b-gptq",
"size_gb_estimate": 38,
"vllm_min_version": "0.4.0",
"vllm": {
"tensor_parallel_size": 4,
"quantization": "gptq",
"dtype": "float16",
"max_model_len": 8192,
"gpu_memory_utilization": 0.88,
"max_num_seqs": 4,
"extra_args": [
"--disable-custom-all-reduce",
"--enforce-eager"
]
},
"runtime_id": "vllm-legacy-040",
"inference_backend": "vllm",
"v100_activate": true,
"v100_block_reason": null
},
{
"id": "qwen25-coder-32b-gptq",
"name": "Qwen 2.5 Coder 32B GPTQ",
"description": "Alibaba Qwen open weights. Top open-source code LLM (GPT-4o class). 4\u00d7 V100.",
"tags": [
"coding",
"opensource",
"qwen",
"v100_ready"
],
"license": "Apache-2.0",
"repo_id": "Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4",
"local_path": "/root/models/qwen25-coder-32b-gptq",
"served_name": "qwen2.5-coder-32b-gptq",
"size_gb_estimate": 20,
"vllm_min_version": "0.4.0",
"vllm": {
"tensor_parallel_size": 4,
"quantization": "gptq",
"dtype": "float16",
"max_model_len": 8192,
"gpu_memory_utilization": 0.9,
"max_num_seqs": 4,
"extra_args": [
"--trust-remote-code",
"--enforce-eager"
]
},
"runtime_id": "vllm-legacy-040",
"inference_backend": "vllm",
"v100_activate": true,
"v100_block_reason": null
},
{
"id": "qwen25-32b-gptq",
"name": "Qwen 2.5 32B GPTQ",
"description": "Alibaba Qwen open weights (general instruct, strong coder).",
"tags": [
"coding",
"opensource",
"qwen",
"v100_ready"
],
"license": "Apache-2.0",
"repo_id": "Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4",
"local_path": "/root/models/qwen25-32b-gptq",
"served_name": "qwen2.5-32b-gptq",
"size_gb_estimate": 20,
"vllm_min_version": "0.4.0",
"vllm": {
"tensor_parallel_size": 4,
"quantization": "gptq",
"dtype": "float16",
"max_model_len": 8192,
"gpu_memory_utilization": 0.9,
"max_num_seqs": 4,
"extra_args": [
"--trust-remote-code",
"--enforce-eager"
]
},
"runtime_id": "vllm-legacy-040",
"inference_backend": "vllm",
"v100_activate": true,
"v100_block_reason": null
},
{
"id": "deepseek-coder-33b-gptq",
"name": "DeepSeek Coder 33B GPTQ",
"description": "DeepSeek open weights (TheBloke GPTQ). Top-tier coder, TP=4.",
"tags": [
"coding",
"deepseek",
"opensource",
"v100_ready"
],
"license": "DeepSeek License",
"repo_id": "TheBloke/deepseek-coder-33B-instruct-GPTQ",
"local_path": "/root/models/deepseek-coder-33b-gptq",
"served_name": "deepseek-coder-33b-gptq",
"size_gb_estimate": 18,
"vllm_min_version": "0.4.0",
"vllm": {
"tensor_parallel_size": 4,
"quantization": "gptq",
"dtype": "float16",
"max_model_len": 4096,
"gpu_memory_utilization": 0.88,
"max_num_seqs": 4,
"extra_args": [
"--trust-remote-code",
"--enforce-eager"
]
},
"runtime_id": "vllm-legacy-040",
"inference_backend": "vllm",
"v100_activate": true,
"v100_block_reason": null
},
{
"id": "qwen25-coder-7b",
"name": "Qwen 2.5 Coder 7B",
"description": "Alibaba Qwen open weights. Fast code model, 1 GPU.",
"tags": [
"coding",
"opensource",
"qwen",
"v100_ready"
],
"license": "Apache-2.0",
"repo_id": "Qwen/Qwen2.5-Coder-7B-Instruct",
"local_path": "/root/models/qwen25-coder-7b",
"served_name": "qwen2.5-coder-7b",
"size_gb_estimate": 15,
"vllm_min_version": "0.4.0",
"vllm": {
"tensor_parallel_size": 1,
"dtype": "float16",
"max_model_len": 8192,
"gpu_memory_utilization": 0.9,
"max_num_seqs": 8,
"extra_args": [
"--trust-remote-code",
"--enforce-eager"
]
},
"runtime_id": "vllm-legacy-040",
"inference_backend": "vllm",
"v100_activate": true,
"v100_block_reason": null
},
{
"id": "deepseek-coder-6.7b",
"name": "DeepSeek Coder 6.7B",
"description": "DeepSeek open weights. Fast lightweight coder, 1 GPU.",
"tags": [
"coding",
"deepseek",
"opensource",
"v100_ready"
],
"license": "DeepSeek License",
"repo_id": "deepseek-ai/deepseek-coder-6.7b-instruct",
"local_path": "/root/models/deepseek-coder-6.7b",
"served_name": "deepseek-coder-6.7b",
"size_gb_estimate": 14,
"vllm_min_version": "0.4.0",
"vllm": {
"tensor_parallel_size": 1,
"dtype": "float16",
"max_model_len": 8192,
"gpu_memory_utilization": 0.9,
"max_num_seqs": 8,
"extra_args": [
"--trust-remote-code",
"--enforce-eager"
]
},
"runtime_id": "vllm-legacy-040",
"inference_backend": "vllm",
"v100_activate": true,
"v100_block_reason": null
},
{
"id": "deepseek-coder-7b",
"name": "DeepSeek Coder 7B v1.5",
"description": "DeepSeek open weights. Balanced 7B coder.",
"tags": [
"coding",
"deepseek",
"opensource",
"v100_ready"
],
"license": "DeepSeek License",
"repo_id": "deepseek-ai/deepseek-coder-7b-instruct-v1.5",
"local_path": "/root/models/deepseek-coder-7b",
"served_name": "deepseek-coder-7b",
"size_gb_estimate": 15,
"vllm_min_version": "0.4.0",
"vllm": {
"tensor_parallel_size": 1,
"dtype": "float16",
"max_model_len": 8192,
"gpu_memory_utilization": 0.9,
"max_num_seqs": 8,
"extra_args": [
"--trust-remote-code",
"--enforce-eager"
]
},
"runtime_id": "vllm-legacy-040",
"inference_backend": "vllm",
"v100_activate": true,
"v100_block_reason": null
},
{
"id": "starcoder2-15b",
"name": "StarCoder2 15B",
"description": "BigCode/Hugging Face. Apache-2.0 code specialist, 1\u20132 GPU.",
"tags": [
"coding",
"opensource",
"v100_ready"
],
"license": "Apache-2.0",
"repo_id": "bigcode/starcoder2-15b",
"local_path": "/root/models/starcoder2-15b",
"served_name": "starcoder2-15b",
"size_gb_estimate": 30,
"vllm_min_version": "0.4.0",
"vllm": {
"tensor_parallel_size": 2,
"dtype": "float16",
"max_model_len": 8192,
"gpu_memory_utilization": 0.9,
"max_num_seqs": 4,
"extra_args": [
"--trust-remote-code",
"--enforce-eager"
]
},
"runtime_id": "vllm-legacy-040",
"inference_backend": "vllm",
"v100_activate": true,
"v100_block_reason": null
},
{
"id": "granite-code-8b",
"name": "IBM Granite Code 8B",
"description": "IBM open weights. Enterprise-friendly Apache-2.0 coder.",
"tags": [
"coding",
"opensource",
"v100_ready"
],
"license": "Apache-2.0",
"repo_id": "ibm-granite/granite-3.3-8b-instruct",
"local_path": "/root/models/granite-code-8b",
"served_name": "granite-code-8b",
"size_gb_estimate": 16,
"vllm_min_version": "0.4.0",
"vllm": {
"tensor_parallel_size": 1,
"dtype": "float16",
"max_model_len": 8192,
"gpu_memory_utilization": 0.9,
"max_num_seqs": 8,
"extra_args": [
"--trust-remote-code",
"--enforce-eager"
]
},
"runtime_id": "vllm-legacy-040",
"inference_backend": "vllm",
"v100_activate": true,
"v100_block_reason": null
},
{
"id": "yi-coder-9b",
"name": "Yi-Coder 9B",
"description": "01.AI open weights. Strong 9B code model, 1 GPU.",
"tags": [
"coding",
"opensource",
"v100_ready"
],
"license": "Apache-2.0",
"repo_id": "01-ai/Yi-Coder-9B-Chat",
"local_path": "/root/models/yi-coder-9b",
"served_name": "yi-coder-9b",
"size_gb_estimate": 18,
"vllm_min_version": "0.4.0",
"vllm": {
"tensor_parallel_size": 1,
"dtype": "float16",
"max_model_len": 8192,
"gpu_memory_utilization": 0.9,
"max_num_seqs": 8,
"extra_args": [
"--trust-remote-code",
"--enforce-eager"
]
},
"runtime_id": "vllm-legacy-040",
"inference_backend": "vllm",
"v100_activate": true,
"v100_block_reason": null
},
{
"id": "deepseek-coder-v2-lite",
"name": "DeepSeek Coder V2 Lite",
"description": "DeepSeek MoE coder (16B/2.4B active). vLLM 0.8 on V100.",
"tags": [
"coding",
"deepseek",
"opensource",
"v100_ready"
],
"license": "DeepSeek License",
"repo_id": "deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct",
"local_path": "/root/models/deepseek-coder-v2-lite",
"served_name": "deepseek-coder-v2-lite",
"size_gb_estimate": 32,
"vllm_min_version": "0.6.0",
"vllm": {
"tensor_parallel_size": 2,
"dtype": "bfloat16",
"max_model_len": 8192,
"gpu_memory_utilization": 0.9,
"max_num_seqs": 4,
"extra_args": [
"--trust-remote-code",
"--enforce-eager"
]
},
"runtime_id": "vllm-modern-080",
"inference_backend": "vllm",
"v100_activate": true,
"v100_block_reason": null
},
{
"id": "qwen3-coder-next",
"name": "Qwen3 Coder Next",
"description": "Alibaba agentic coder (80B MoE, 3B active). vLLM 0.8 on V100.",
"tags": [
"coding",
"opensource",
"qwen",
"v100_ready"
],
"license": "Apache-2.0",
"repo_id": "Qwen/Qwen3-Coder-Next",
"local_path": "/root/models/qwen3-coder-next",
"served_name": "qwen3-coder-next",
"size_gb_estimate": 45,
"vllm_min_version": "0.8.0",
"vllm": {
"tensor_parallel_size": 4,
"dtype": "bfloat16",
"max_model_len": 8192,
"gpu_memory_utilization": 0.9,
"max_num_seqs": 4,
"extra_args": [
"--trust-remote-code",
"--enforce-eager"
]
},
"runtime_id": "vllm-modern-080",
"inference_backend": "vllm",
"v100_activate": true,
"v100_block_reason": null
},
{
"id": "qwen3-coder-30b",
"name": "Qwen3 Coder 30B A3B",
"description": "Alibaba MoE agentic coder. vLLM 0.8 on V100.",
"tags": [
"coding",
"opensource",
"qwen",
"v100_ready"
],
"license": "Apache-2.0",
"repo_id": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
"local_path": "/root/models/qwen3-coder-30b",
"served_name": "qwen3-coder-30b",
"size_gb_estimate": 60,
"vllm_min_version": "0.8.0",
"vllm": {
"tensor_parallel_size": 4,
"dtype": "bfloat16",
"max_model_len": 8192,
"gpu_memory_utilization": 0.9,
"max_num_seqs": 4,
"extra_args": [
"--trust-remote-code",
"--enforce-eager"
]
},
"runtime_id": "vllm-modern-080",
"inference_backend": "vllm",
"v100_activate": true,
"v100_block_reason": null
},
{
"id": "qwen36-27b",
"name": "Qwen 3.6 27B",
"description": "Qwen open weights (dense). On V100 via SGLang \u2014 prefer AWQ variant.",
"tags": [
"coding",
"opensource",
"qwen",
"v100_via_sglang"
],
"license": "Apache-2.0",
"repo_id": "Qwen/Qwen3.6-27B",
"local_path": "/root/models/qwen36-27b",
"served_name": "qwen3.6-27b",
"size_gb_estimate": 54,
"vllm_min_version": "0.19.0",
"vllm": {
"tensor_parallel_size": 4,
"dtype": "bfloat16",
"max_model_len": 8192,
"gpu_memory_utilization": 0.9,
"max_num_seqs": 4,
"extra_args": [
"--trust-remote-code",
"--enforce-eager"
]
},
"runtime_id": "sglang-modern",
"inference_backend": "sglang",
"v100_activate": true,
"v100_block_reason": null
},
{
"id": "qwen36-27b-awq",
"name": "Qwen 3.6 27B AWQ",
"description": "Qwen open weights (AWQ). Primary Qwen 3.6 path on V100 via SGLang.",
"tags": [
"coding",
"opensource",
"qwen",
"v100_via_sglang"
],
"license": "Apache-2.0",
"repo_id": "QuantTrio/Qwen3.6-27B-AWQ",
"local_path": "/root/models/qwen36-27b-awq",
"served_name": "qwen3.6-27b-awq",
"size_gb_estimate": 16,
"vllm_min_version": "0.19.0",
"vllm": {
"tensor_parallel_size": 4,
"quantization": "awq",
"dtype": "float16",
"max_model_len": 8192,
"gpu_memory_utilization": 0.9,
"max_num_seqs": 8,
"extra_args": [
"--trust-remote-code",
"--enforce-eager"
]
},
"runtime_id": "sglang-modern",
"inference_backend": "sglang",
"v100_activate": true,
"v100_block_reason": null
},
{
"id": "codellama-34b",
"name": "Code Llama 34B",
"description": "Meta open weights (custom license). Classic code LLM \u2014 downloadable via HF.",
"tags": [
"coding",
"opensource",
"v100_ready"
],
"license": "Llama 3 Community License",
"repo_id": "codellama/CodeLlama-34b-Instruct-hf",
"local_path": "/root/models/codellama-34b",
"served_name": "codellama-34b",
"size_gb_estimate": 68,
"vllm_min_version": "0.4.0",
"vllm": {
"tensor_parallel_size": 4,
"dtype": "float16",
"max_model_len": 4096,
"gpu_memory_utilization": 0.9,
"max_num_seqs": 2,
"extra_args": [
"--enforce-eager"
]
},
"runtime_id": "vllm-legacy-040",
"inference_backend": "vllm",
"v100_activate": true,
"v100_block_reason": null
}
]
}
config/model-manager/vm-specs.json
+14
View File
@@ -0,0 +1,14 @@
{
"vmid": 303,
"name": "atc-gpu-dev",
"proxmox_host": "atc-gpu",
"ip": "10.0.20.106",
"cpu_model": "Intel Xeon Gold 6148 @ 2.40GHz",
"vcpu": 32,
"sockets": 2,
"cores_per_socket": 16,
"memory_gib": 128,
"disk_gib": 250,
"gpu": "4× Tesla V100 PCIe 32GB",
"os": "Rocky Linux 9"
}