Continuous Batching in LLM Serving: How Throughput Scales

Continuous batching (also called in-flight batching) is the technique that made modern LLM serving scalable. Without it, serving 10 concurrent users requires 10x the GPU capacity of 1 user. With continuous batching, GPU utilization becomes near-100% regardless of user count. Understanding it helps you choose and configure serving infrastructure.

Why it matters: An RTX 4090 with continuous batching can serve a small team as effectively as multiple single-user setups. For hardware matched to your team size, LLMHardware.io has team server guides.

The Problem: Static Batching Waste

In naive static batching, requests are grouped before inference starts. If user A's request completes at step 50 while user B's continues to step 200, the GPU is idle for user A's "slot" from step 50-200. At high concurrency, most GPU cycles are wasted waiting for slow requests to complete before the batch can be refilled. Real-world GPU utilization with static batching is often 20-40%.

Continuous Batching Solution

Continuous batching inserts new requests into the batch as soon as a slot frees up — mid-generation. When user A's request completes, user C's request immediately takes the slot. The GPU is always running at maximum batch size, with finished requests cycling out and new ones cycling in dynamically. GPU utilization jumps to 80-95% at sufficient load. This is what powers OpenAI's API serving hundreds of thousands of concurrent users on a fixed hardware cluster.

Implementation in Local Serving

vLLM and TGI both implement continuous batching by default. llama.cpp server uses --cont-batching to enable it. The key configuration: set --parallel N (llama.cpp) or --max-num-seqs N (vLLM) to the maximum number of concurrent requests you want to support. Higher values improve throughput at the cost of slightly higher per-request latency. For a 4-person team, 4-8 concurrent slots is typical; for a 20-person team, 16-32.

Comments

Post a Comment

Popular posts from this blog

AMD RX 9070 XT for Local LLMs: ROCm Performance Guide (2026)

The AMD RX 9070 XT launched in early 2026 at $599 with 16GB GDDR6 and 648 GB/s memory bandwidth. For local LLM users who want a mid-range GPU without NVIDIA prices, this changes the calculus significantly. Here is what it actually delivers. RX 9070 XT Specs vs Competition GPU VRAM Bandwidth Price LLM Score RX 9070 XT 16 GB 648 GB/s $599 ~60 tok/s RTX 4070 Ti Super 16 GB 672 GB/s $799 ~62 tok/s RTX 4080 Super 16 GB 736 GB/s $999 ~68 tok/s RTX 4090 24 GB 1,008 GB/s ~$1,100 ~90 tok/s At $599 with 16GB VRAM, the RX 9070 XT is the best value GPU for local LLMs in the mid-range tier in 2026. See the full comparison at LLMHardware.io's AMD GPU guide . ROCm Setup on Linux (2026) # Ubuntu 22.04/24.04 sudo apt install rocm-hip-libraries hip-base # or use the AMD installer: wget https://repo.radeon.com/amdgpu-install/6.3/ubuntu/jammy/amdgpu-install_6.3.60300-1_all.deb sudo dpkg -i amdgpu-install*.deb sudo amdgpu-install --usecase=rocm,lrt,openclsdk # Verify ROCm sees your GPU r...
Read more

llama.cpp flash attention: how to enable and benchmark

Image
Flash attention computes attention with far less memory traffic. The math is identical; the memory movement is not. In llama.cpp it matters most in two situations: long context windows and tight video memory (VRAM). With flash attention enabled, the key-value cache shrinks substantially. A 32k-token context window becomes realistic on a 16GB card, and the prompt-processing phase speeds up, so long documents get ingested faster. The catch is compatibility: not every model and quantization combination supports it, and on some setups the speedup is modest. If you run short chats on a strong GPU, you may barely notice. Where it shines is retrieval-augmented generation (RAG) and long-document work on mid-range cards. Enable it, compare your tokens per second, and keep it if your workload benefits. For the common case of pasting a long PDF and asking questions, it is close to free performance. See how context length changes VRAM needs .
Read more

SillyTavern with Local LLMs: Complete Setup for AI Companions

Image
SillyTavern is the most feature-rich frontend for character-based AI conversations. What began as an AI roleplay tool has evolved into a powerful platform with persona management, memory systems, extensive prompt engineering tools, and connections to every major local inference backend. Here's how to set it up with local models. Quick connect: SillyTavern connects to Ollama, KoboldCpp, llama.cpp server, and TabbyAPI (ExLlamaV2) out of the box. Any of the hardware setups at LLMHardware.io provides a solid backend for SillyTavern. Installation Install via git: git clone https://github.com/SillyTavern/SillyTavern && cd SillyTavern && npm install then node server.js . Access at localhost:8000. For persistent installation, use the included start.sh script. SillyTavern uses Node.js and runs on any platform. The companion app (STMP) enables mobile access to your SillyTavern instance via Tailscale or local network. Character Cards and the TavernAI Format Chara...
Read more