cjw/amd-r9700-ai-toolboxes
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

updated benchmarks

Browse Source
This commit is contained in:
Donato Capitella
2025-11-30 08:20:12 +00:00
parent 82c6e04253
commit 7b4006b1d4
4 changed files with 51 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/assets/index2.js
+15 -15
View File
@@ -57,9 +57,9 @@ function cacheUI() {
hipblasModalOpen: document.getElementById("hipblas-modal-open"),
hipblasModal: document.getElementById("hipblas-modal"),
hipblasModalClose: document.getElementById("hipblas-modal-close"),
rpcModalOpen: document.getElementById("rpc-modal-open"),
rpcModal: document.getElementById("rpc-modal"),
rpcModalClose: document.getElementById("rpc-modal-close"),
dualModalOpen: document.getElementById("dual-modal-open"),
dualModal: document.getElementById("dual-modal"),
dualModalClose: document.getElementById("dual-modal-close"),
rocwmmaModalOpen: document.getElementById("rocwmma-modal-open"),
rocwmmaModal: document.getElementById("rocwmma-modal"),
rocwmmaModalClose: document.getElementById("rocwmma-modal-close"),
@@ -77,9 +77,9 @@ function setupModals() {
close: state.ui.hipblasModalClose,
},
{
open: state.ui.rpcModalOpen,
modal: state.ui.rpcModal,
close: state.ui.rpcModalClose,
open: state.ui.dualModalOpen,
modal: state.ui.dualModal,
close: state.ui.dualModalClose,
},
{
open: state.ui.rocwmmaModalOpen,
@@ -186,7 +186,7 @@ function ensureModel(testEntry, modelName, run) {
quant: (run.quant || "Unknown").toUpperCase(),
sizeB: run.name_params_b ?? run.params_b ?? null,
backends: {},
isRpc: Boolean(run.rpc),
isDual: run.gpu_config === "dual",
search_blob: [modelName, run.quant, run.env, run.test]
.filter(Boolean)
.map((s) => s.toString().toLowerCase())
@@ -202,10 +202,10 @@ function ensureModel(testEntry, modelName, run) {
state.sizeStats.min = Math.min(state.sizeStats.min, row.sizeB);
state.sizeStats.max = Math.max(state.sizeStats.max, row.sizeB);
}
if (run.rpc) {
row.isRpc = true;
if (!row.search_blob.includes("rpc")) {
row.search_blob = `${row.search_blob} rpc`;
if (run.gpu_config === "dual") {
row.isDual = true;
if (!row.search_blob.includes("dual")) {
row.search_blob = `${row.search_blob} dual`;
}
}
return row;
@@ -462,11 +462,11 @@ function buildSingleTable(models, backendList) {
nameSpan.className = "model-name";
nameSpan.textContent = model.model;
head.appendChild(nameSpan);
if (model.isRpc) {
if (model.isDual) {
const pill = document.createElement("span");
pill.className = "model-pill model-pill-rpc";
pill.title = "Run executed via llama.cpp RPC across two servers";
pill.textContent = "RPC · dual server";
pill.className = "model-pill model-pill-dual";
pill.title = "Run executed on Dual GPU (2x R9700)";
pill.textContent = "Dual GPU";
head.appendChild(pill);
}
tdModel.appendChild(head);
docs/index.html
+9 -13
View File
@@ -21,8 +21,8 @@
<button id="hipblas-modal-open" type="button" class="chip small legend-pill legend-pill-default">
hipBLASLt vs hblt0
</button>
<button id="rpc-modal-open" type="button" class="chip small legend-pill legend-pill-rpc">
RPC · dual server
<button id="dual-modal-open" type="button" class="chip small legend-pill legend-pill-dual">
Dual GPU
</button>
<button id="rocwmma-modal-open" type="button" class="chip small legend-pill legend-pill-rocwmma">
rocWMMA
@@ -103,18 +103,14 @@
</div>
</div>
<div id="rpc-modal" class="modal hidden" role="dialog" aria-modal="true" aria-labelledby="rpc-title">
<div id="dual-modal" class="modal hidden" role="dialog" aria-modal="true" aria-labelledby="dual-title">
<div class="modal-content">
<button id="rpc-modal-close" class="modal-close" aria-label="Close dialog">×</button>
<h2 id="rpc-title">RPC · dual server</h2>
<p>These results were produced with two R9700 systems (each 32&nbsp;GB)
connected over 5&nbsp;Gbps Ethernet. One runs <code>rpc-server</code> from llama.cpp; the other runs
<code>llama-bench --rpc</code>.
</p>
<p>This setup allows distributed inference, splitting large GGUF models across both machines. The metric
shows what
you can expect when latency is limited by the network and the workload is balanced between two RPC
participants.</p>
<button id="dual-modal-close" class="modal-close" aria-label="Close dialog">×</button>
<h2 id="dual-title">Dual GPU (2x R9700)</h2>
<p>These results were produced using two AMD Radeon AI PRO R9700 GPUs (32GB each, 64GB total).</p>
<p>Models larger than ~30GB are automatically distributed across both GPUs using
<code>HIP_VISIBLE_DEVICES=0,1</code>. Smaller models run on a single GPU
(<code>HIP_VISIBLE_DEVICES=0</code>).</p>
</div>
</div>