// TOPIC

#serving

10 articles

◆◆IntermediateDeepSeekMistral
01

Mixture of Experts: why every frontier model went sparse

How mixture of experts works — routers, top-k selection, shared experts — and the VRAM and batching math that decides when sparse models save you money.

#llm-internals#inference#serving
17 min
◆◆◆AdvancedNVIDIAHugging Face
02

Deploying LLM Workloads: GPUs, Kubernetes, and Serverless

Where LLM serving engines actually run: GPU cloud choices, Kubernetes patterns, serverless GPU tradeoffs, cold starts, and autoscaling strategies that hold up under real traffic.

#serving#inference#llmops
17 min
◆◆◆AdvancedNVIDIAHugging Face
03

Throughput vs Latency: The GPU Economics of LLM Serving

How tokens/sec, cost per token, TTFT SLAs, and GPU utilization interact — and the engineering decisions that separate a profitable inference deployment from a money pit.

#inference#serving#cost-optimization
16 min
◆◆IntermediateNVIDIAHugging Face
04

Choosing a serving engine: vLLM, SGLang, TensorRT-LLM, and Ollama in 2026

A decision framework for picking the right LLM inference engine based on workload, hardware, and ops complexity — grounded in 2025-2026 benchmarks.

#inference#serving#quantization
15 min
◆◆Intermediate
05

Speculative decoding: 2-3x latency speedup without changing model quality

How a small draft model proposes tokens the large target verifies in parallel — and why rejection sampling guarantees identical output distributions with real speedup numbers.

#inference#serving#latency
16 min
◆◆IntermediateOpenAIAnthropic
06

Streaming, Batching, and Throughput: Latency vs Cost Trade-offs in Production

How streaming, continuous batching, and async batch APIs interact with latency and cost — and how to configure each without destroying p99 for interactive users.

#inference#serving#cost-optimization
14 min
◆◆IntermediateNVIDIAHugging Face
07

Quantization Demystified: GPTQ, AWQ, GGUF, and FP8 With Real Tradeoffs

A practical comparison of GPTQ, AWQ, GGUF, and FP8 quantization formats — memory math, quality loss, hardware targets, and when each format actually wins in production.

#quantization#inference#serving
16 min
BeginnerNVIDIAHugging Face
08

Continuous Batching and Scheduling: Why Static Batching Wastes 70% of Your GPU

How iteration-level scheduling replaced static batching and became the single biggest serving optimization available without any model changes — with real numbers.

#inference#serving#latency
16 min
BeginnerNVIDIAHugging Face
09

The KV Cache: GPU Memory Math Every Serving Engineer Must Know

A concrete formula for how much GPU memory your KV cache consumes, why it scales brutally with context length, and the PagedAttention trick that fixes it.

#inference#serving#llm-internals
16 min
Beginner
10

Prefill vs Decode: The Two Phases of Every LLM Request

Why the first token takes longer than every other token, how compute-bound prefill and bandwidth-bound decode shape your entire serving architecture, and what to do about it.

#inference#serving#latency
13 min