2nd/10_Wiki/Topics/AI_and_ML/Scalability-in-AI-Systems.md

---
id: wiki-2026-0508-scalability-in-ai-systems
title: Scalability in AI Systems
category: 10_Wiki/Topics
status: verified
canonical_id: self
aliases: [AI Scalability, Distributed Training, LLM Scaling]
duplicate_of: none
source_trust_level: A
confidence_score: 0.9
verification_status: applied
tags: [scalability, distributed-training, inference, vllm, fsdp, llm]
raw_sources: []
last_reinforced: 2026-05-10
github_commit: pending
tech_stack:
  language: Python
  framework: PyTorch / vLLM / DeepSpeed
---

# Scalability in AI Systems

## 매 한 줄
> **"매 model size × data × users × latency 의 4축 동시 만족 — 매 single GPU → multi-node training (FSDP/ZeRO/TP/PP) 과 매 10K+ QPS inference (vLLM/SGLang/PagedAttention) 의 양 갈래"**. 매 2020 GPT-3 (175B) 부터 매 2026 trillion-param MoE (Llama 4 Behemoth, Claude Opus 4.7, GPT-5) 까지 매 scaling laws (Chinchilla, Hoffmann 2022) 가 산업 의 compass.

## 매 핵심

### 매 Training scalability axes
- **Data parallel (DP)**: replicate model, shard batch — gradient all-reduce.
- **Tensor parallel (TP)**: split single layer across GPUs (Megatron-LM).
- **Pipeline parallel (PP)**: split layers across stages (GPipe, 1F1B).
- **FSDP / ZeRO**: shard params + grads + optimizer state (ZeRO-1/2/3).
- **Sequence/Context parallel**: shard along sequence (Ring Attention, DeepSpeed-Ulysses).
- **MoE expert parallel**: route tokens to expert subsets across GPUs.

### 매 Inference scalability
- **Continuous batching**: vLLM / TGI — token-level scheduling, no head-of-line block.
- **PagedAttention**: KV cache paged like virtual memory → high concurrency.
- **Prefix caching**: shared system prompt cache (vLLM, SGLang).
- **Speculative decoding**: small draft model proposes, large verifies → 2-3x.
- **Quantization**: FP8, INT4 (AWQ, GPTQ), MX formats (MXFP4) — 2026 H200/B200 native.
- **Disaggregated serving**: prefill nodes vs decode nodes (Splitwise, DistServe).

### 매 응용
1. Pretraining 70B+ on 256+ GPU cluster.
2. LoRA/QLoRA fine-tune on single H100 (24GB shard).
3. 100K+ concurrent chatbot QPS via vLLM cluster.
4. RAG at 1M+ docs with sharded vector DB.
5. Multi-tenant inference with tenant-aware caching.

## 💻 패턴

### FSDP2 with PyTorch (2026 idiom)
```python
import torch
from torch.distributed.fsdp import fully_shard, MixedPrecisionPolicy

model = LlamaForCausalLM.from_pretrained("meta-llama/Llama-3.1-70B")
mp_policy = MixedPrecisionPolicy(
    param_dtype=torch.bfloat16,
    reduce_dtype=torch.float32,
)
for layer in model.model.layers:
    fully_shard(layer, mp_policy=mp_policy)
fully_shard(model, mp_policy=mp_policy)

# Gradient checkpointing for memory
model.gradient_checkpointing_enable()
```

### DeepSpeed ZeRO-3 config
```json
{
  "train_batch_size": 1024,
  "gradient_accumulation_steps": 4,
  "bf16": {"enabled": true},
  "zero_optimization": {
    "stage": 3,
    "offload_param": {"device": "cpu"},
    "offload_optimizer": {"device": "nvme", "nvme_path": "/mnt/nvme"},
    "overlap_comm": true,
    "contiguous_gradients": true
  }
}
```

### vLLM serving (continuous batching + prefix cache)
```python
from vllm import LLM, SamplingParams

llm = LLM(
    model="meta-llama/Llama-3.1-70B-Instruct",
    tensor_parallel_size=4,
    enable_prefix_caching=True,
    max_model_len=128000,
    quantization="fp8",
    gpu_memory_utilization=0.92,
)
out = llm.generate(prompts, SamplingParams(max_tokens=512, temperature=0.7))
```

### SGLang RadixAttention (shared prefix tree)
```python
import sglang as sgl

sgl.set_default_backend(sgl.RuntimeEndpoint("http://localhost:30000"))

@sgl.function
def multi_turn(s, system, turns):
    s += sgl.system(system)  # cached across all calls
    for t in turns:
        s += sgl.user(t["q"]) + sgl.assistant(sgl.gen(max_tokens=256))

# Massive throughput when many users share system prompt
```

### Speculative decoding (vLLM)
```python
llm = LLM(
    model="meta-llama/Llama-3.1-70B-Instruct",
    speculative_model="meta-llama/Llama-3.2-1B-Instruct",
    num_speculative_tokens=5,
    use_v2_block_manager=True,
)
```

### Megatron-LM tensor + pipeline parallel
```bash
torchrun --nproc_per_node=8 --nnodes=8 \
  pretrain_gpt.py \
  --tensor-model-parallel-size 8 \
  --pipeline-model-parallel-size 8 \
  --num-layers 80 --hidden-size 8192 \
  --num-attention-heads 64 --seq-length 8192 \
  --micro-batch-size 1 --global-batch-size 1024 \
  --bf16 --use-flash-attn
```

### Distributed inference K8s (vLLM + Ray Serve)
```python
from ray import serve
from vllm.entrypoints.openai.api_server import app as vllm_app

@serve.deployment(num_replicas=4, ray_actor_options={"num_gpus": 2})
@serve.ingress(vllm_app)
class LLMService:
    def __init__(self, model):
        self.engine = AsyncLLMEngine.from_engine_args(
            AsyncEngineArgs(model=model, tensor_parallel_size=2)
        )
```

### KV cache sizing rule of thumb
```python
def kv_cache_bytes(layers, hidden_dim, seq_len, batch, dtype_bytes=2, kv_heads=None):
    h = kv_heads or hidden_dim  # GQA: kv_heads < hidden
    return 2 * batch * layers * seq_len * h * dtype_bytes
# Llama-3-70B at 128K context, batch=1, GQA(8): ~10 GB KV
```

### Disaggregated prefill/decode (Splitwise pattern)
```python
# Prefill cluster: H100, optimized for compute
# Decode cluster: H100/L40S, optimized for memory bandwidth
# KV transfer over NVLink/RDMA between clusters
prefill_resp = await prefill_client.prefill(prompt)  # returns KV blocks ref
decode_stream = decode_client.decode(kv_ref=prefill_resp.kv_ref, max_tokens=512)
```

## 매 결정 기준
| 상황 | Approach |
|---|---|
| <13B model train | DDP / FSDP1 single node 8xGPU |
| 70B train | FSDP2 / ZeRO-3 multi-node + activation checkpoint |
| 400B+ MoE | TP + PP + EP + ZeRO-1 (Megatron-Core / NeMo) |
| Chatbot serving | vLLM + prefix cache + speculative decoding |
| Long context (1M+) | Ring attention / context parallel |
| High concurrency | SGLang RadixAttention + disaggregated |

**기본값**: FSDP2 for training under 100B; vLLM with FP8 + prefix cache + spec decoding for serving.

## 🔗 Graph
- 부모: [[Distributed-Systems]]
- 변형: [[Pipeline-Parallelism]]
- 응용: [[Fine-tuning]]
- Adjacent: [[LLM_Optimization_and_Deployment_Strategies|vLLM]] · [[Flash-Attention]] · [[LLM_Optimization_and_Deployment_Strategies|Quantization]]

## 🤖 LLM 활용
**언제**: capacity planning estimates, config-file generation (deepspeed, accelerate), debugging OOM via log triage, scaling-law back-of-envelope.
**언제 X**: actually scheduling kernels — the orchestrator (PyTorch/vLLM) handles deterministic scheduling.

## ❌ 안티패턴
- **All-reduce on tiny gradients**: communication dominates; bucket gradients.
- **Naive batching for serving**: head-of-line blocking — use continuous batching.
- **Unbounded KV cache**: OOM at peak; use PagedAttention + admission control.
- **No prefix cache for shared system prompt**: 5-10x throughput left on table.
- **PP without enough microbatches**: bubble dominates pipeline.
- **MoE without expert balance loss**: dead experts, capacity waste.

## 🧪 검증 / 중복
- Verified (Megatron-LM/Megatron-Core, vLLM paper SOSP 2023, Chinchilla 2022, NVIDIA H100/B200 perf guides 2026).
- 신뢰도 A.

## 🕓 Changelog
| 날짜 | 변경 |
|---|---|
| 2026-05-08 | Phase 1 |
| 2026-05-10 | Manual cleanup — FSDP/ZeRO/TP/PP, vLLM/SGLang, disaggregated serving |