engineering/lumbda
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

bend.html: drop false port claim — qwen runs on GPU, not on ports 9090/9091

Browse source 
Earlier commit incorrectly named ports 9090+9091 as qwen LLM serving.
Agent's actual finding (ai.foxhop.net second-worker deployment) was
uid-992 Erlang Cowboy services on those ports — unsandbox infra,
not qwen. Qwen runs on the GPU itself, not on those TCP ports.

The coexistence story (our bend kernels share a 4090 with qwen
because we burn SMs for ms-at-a-time then release) stays intact;
the false port attribution removed.
This commit is contained in:
russell@unturf.com 2026-06-05 20:58:05 -04:00
parent 7b67b727e1
commit 01a36f3fcd
No known key found for this signature in database
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
www/bend.html
View file

@ -100,11 +100,11 @@ make gpu-worker LUMBDA=asm # smallest footprint</code></pre>
<thead><tr><th>host</th><th>GPU</th><th>arch</th><th>port</th><th>daemons live</th><th>coexists with</th></tr></thead>
<tbody>
<tr><td><code>3090-ai.foxhop.net</code></td><td>RTX 3090 (24 GB)</td><td>sm_86</td><td>9091</td><td>shake / cgbn / secp / sim-ops-bin / sim-axis-flip</td><td>idle</td></tr>
<tr><td><code>ai.foxhop.net</code></td><td>RTX 4090 (24 GB)</td><td>sm_89</td><td>9092</td><td>shake / cgbn / secp</td><td>qwen LLM serving on ports 9090 + 9091 (Erlang Cowboy, uid 992)</td></tr>
<tr><td><code>ai.foxhop.net</code></td><td>RTX 4090 (24 GB)</td><td>sm_89</td><td>9092</td><td>shake / cgbn / secp</td><td>qwen LLM on GPU</td></tr>
</tbody>
</table>
<p>The 4090 box shares the GPU with a qwen LLM (vllm) serving on the same machine. Our bend kernels fit alongside qwen comfortably because the secp256k1 / CGBN workloads burn the SMs only for milliseconds at a time, then release. The qwen server keeps its model weights resident; our kernels allocate transient VRAM for the per-call batch, run, free, return. 24 GB VRAM is enough for both.</p>
<p>The 4090 box shares the GPU with a qwen LLM (vllm). Our bend kernels fit alongside qwen comfortably because the secp256k1 / CGBN workloads burn the SMs only for milliseconds at a time, then release. The qwen server keeps its model weights resident; our kernels allocate transient VRAM for the per-call batch, run, free, return. 24 GB VRAM is enough for both.</p>
<h3>Cross-GPU parity at small batches</h3>
<p>Single-call kernel time at <code>n=100k</code> CGBN 256-bit mod-mul:</p>