gpu-unlock lifts the half-rate cap on RTX 3090 BF16 tensor cores: matrix math 61 to 91% faster, vLLM prefill up 13 to 20%, no decode gain.
Badges
Badges come from GitHub once the author claims this feed.
Recent posts
every link opens the author’s post-
gpu-unlock on Two RTX 3090s: Faster Prefill, No Decode Gain
-
GPU P2P On vs Off: Tensor Parallel LLM Serving on Four R9700s
With GPU peer-to-peer (P2P) off, four Radeon AI PRO R9700s at tensor parallel 4 lost 45 to 55% of prefill speed, 30% of decode and 53% of 16-client throughput.
-
Fitting Four 32 GB Resizable BARs Behind a PCIe Switch on Linux
Linux 7.0 sized a PCIe switch's bridge window too small for four 32 GB GPU BARs (can't assign; no space).
-
Counting PCI Address Space for Resizable BAR on Six GPUs
Why a motherboard with 128 GB of RAM won't POST with Resizable BAR on six GPUs: its 64-bit PCI window only has room for five 32 GB BARs.
-
Six GPUs on One x16 Slot: R9700s and RTX 3090s Behind a PCIe Switch
Four Radeon AI PRO R9700s and two RTX 3090s behind a PEX88096 switch on one X570 slot: BIOS, kernel flags, ROCm and CUDA, and Qwen3.8-27B at 601 tok/s.
-
PCIe Bifurcation vs PCIe Switches and Retimers for Multi-GPU Builds
What bifurcation risers, retimers and PCIe switch (PLX) cards do for a multi-GPU box, with peer-to-peer copies at 54.7 GB/s inside a PEX88096 and what ACS costs.