BenHamm

OpenClaw - GLM-5-FP8 Inference Benchmark Report: 8×B200 vs 8×H200

Date: 2026-02-13
Model: zai-org/GLM-5-FP8 (744B MoE, 40B active parameters)
Framework: SGLang (lmsysorg/sglang:glm5-blackwell)
Hardware: 8× NVIDIA B200 183GB, NV18 NVSwitch, Xeon 8570 (224 cores), 2TB RAM
Reference: SGLang GLM-5 Cookbook (8×H200 141GB) AI Agent: Claude-4.6-Opus Running on OpenClaw

---

BenHamm

Qwen3-32B Disaggregated Serving Benchmark Results

Date: December 17, 2024
Model: Qwen/Qwen3-32B-FP8
Cluster: Nebius H200 (16 GPUs)
Framework: TensorRT-LLM via Dynamo

---

1. Cluster Configuration

BenHamm

AIConfigurator: Fast-Track Your LLM Deployment on NVIDIA Dynamo

What is NVIDIA Dynamo?

NVIDIA Dynamo is a high-throughput, low-latency inference framework for serving generative AI models across multi-node GPU clusters. As LLMs grow beyond what a single GPU can handle, Dynamo solves the orchestration challenge of coordinating shards, routing requests, and transferring KV cache data across distributed systems.

Key capabilities:

• Disaggregated serving — Separates prefill and decode phases for optimized GPU utilization
• KV-aware routing — Routes requests to workers with the highest cache hit rate
• KV Block Manager — Offloads KV cache to CPU, SSD, or remote memory (G2/G3/G4) for higher throughput

BenHamm

AIConfigurator Performance Prediction Mismatch

Summary

We tested AIConfigurator (version 0.4.0) against the performance claims in the "Advanced Disagg Perf Tuning" guide and found a significant discrepancy between AIC's predictions and the guide's reported results.

Key Finding: AIC predicts disaggregated serving provides 7-8% improvement, while the guide reports 102-148% improvement - a 10-20x difference in expected gains.

Source Document: The guide being tested is from PR #4655 by davilu-nvidia (submitted Nov 27, 2025, currently under review and not yet merged).

BenHamm

AIPerf: Comprehensive LLM Benchmarking

Presentation Date: November 13, 2025
Tool: AIPerf v0.3.0

---

Table of Contents

1. Setup: Installing AIPerf 0.3.0

BenHamm

Block Hash: Privacy-Preserving LLM Trace Sharing

The Problem

Inference providers that want to contribute to open soruce projects are limited in what they can share while respecting user privacy and protecting proprietary prompts. Real LLM inference traces contain sensitive information, but without realistic traces, benchmarks can't accurately reflect production workloads.

The Solution

Block hashing converts tokens into cryptographic hash IDs that preserve prefix-matching patterns while protecting content. Based on Mooncake AI's approach (USENIX FAST'25).

BenHamm

AIPerf Benchmark: Claude Sonnet 4.5 via NVIDIA API

Overview

Performance benchmark of aws/anthropic/bedrock-claude-sonnet-4-5-v1 model hosted on NVIDIA's inference API, testing with large context windows (8K input tokens, 1K output tokens).

Benchmark Date: November 3, 2025
Tool: AIPerf v0.2.0
Test Configuration: 100 requests with streaming enabled

BenHamm

Brev Instance Alert Setup for macOS - Never forget to stop your instances!

Brev Instance Alert Setup for macOS

Never forget to stop your Brev instances again! This setup creates an alert that pops up every 4 hours if you have running Brev instances.

What the Alert Looks Like

BenHamm

Qwen3-32B Disaggregation Performance Analysis

Date: October 22, 2025
Environment: Nebius H200 Kubernetes Cluster
Infrastructure: Dynamo LLM Serving Platform v0.5.0
Model: Qwen/Qwen3-32B with FP8 quantization

---

1. Executive Summary

BenHamm

AIPerf Profiling of Text, Image, & Embeddings Endpoints

This tutorial captures end-to-end reference flows for running AIPerf against vLLM-hosted models. Each chapter covers a specific OpenAI-compatible endpoint: how to launch the vLLM server, run the AIPerf benchmark, and interpret