←
Home
Posts
Tags
About
Projects
Subscribe
doug.sh
Building things with keyboards and end mills. Rabbit holes included.
Llm
2026
Nov 11
gpu-unlock on Two RTX 3090s: Faster Prefill, No Decode Gain
linux
gpu
nvidia
kernel
llm
vllm
qwen
self-hosted
Nov 11
GPU P2P On vs Off: Tensor Parallel LLM Serving on Four R9700s
llm
self-hosted
gpu
pcie
amd
rocm
qwen
linux
Nov 9
Fitting Four 32 GB Resizable BARs Behind a PCIe Switch on Linux
linux
pcie
gpu
rocm
amd
nvidia
kernel
llm
self-hosted
Nov 9
Counting PCI Address Space for Resizable BAR on Six GPUs
linux
pcie
gpu
amd
nvidia
llm
self-hosted
Nov 8
Six GPUs on One x16 Slot: R9700s and RTX 3090s Behind a PCIe Switch
llm
ai
self-hosted
gpu
pcie
amd
nvidia
rocm
vllm
qwen
linux
Nov 8
PCIe Bifurcation vs PCIe Switches and Retimers for Multi-GPU Builds
pcie
gpu
nvidia
amd
linux
self-hosted
llm
Sep 27
Debugging PCIe Link Retraining on an x8/x8 Splitter with Two RTX 3090s
llm
ai
self-hosted
gpu
pcie
nvidia
vllm
claude-code
linux
Sep 23
Custom Models in Oh My Pi: vLLM, llama.cpp, SGLang and More
llm
ai
agents
self-hosted
oh-my-pi
qwen
vllm
llama-cpp
sglang
bifrost
Sep 15
Keeping vLLM's Prefix Cache Warm Between Agent Turns
llm
ai
agents
self-hosted
vllm
gpu
qwen
oh-my-pi
mcp
bifrost
Sep 13
Tuning a Local Coding Agent: Oh My Pi and Qwen3.8-27B on Two RTX 3090s
llm
ai
agents
self-hosted
oh-my-pi
qwen
vllm
gpu
Apr 23
Give Your Coding Agent a Journal
claude-code
llm
ai
agents