We just shipped GPU topology health in zymtrace 🚀
Zymtrace now connects GPU topology and health data directly to the workload profile and performance metrics, so you can quickly see when the hardware, or the code, is causing the slowdown.
And zymtrace doesn’t just surface the problem. It tells you what to do about it. If a process lands on the wrong NUMA node, for example, zymtrace gives you the exact numactl command to fix it.
Check it out: zymtrace.com/article/gpu-top…
Re point 1, worth checking out @zymtrace. An eBPF-powered profiling platform which squeezes more FLOPs from your existing infra. From the team behind OpenTelelemetry’s eBPF profiler
We’re attending @RaiseSummit!
Building or considering disaggregated infrastructure across NVIDIA GPUs, AMD GPUs, AWS Trainium, TPUs, or other accelerators?
We’d love to connect.
@zymtrace 💚 @Walmart
We are excited to partner with Walmart to build a heterogeneous AI infrastructure observability layer tailored for general-purpose and GPU-accelerated workloads.
🚀 NVTX in @zymtrace AI flamegraphs.
For the first time, NVTX annotations can now be viewed directly inside an AI flamegraph, connecting application context to the GPU work it triggered.
NVTX adds labels that describe application-level regions: model layers, inference phases, tensor shapes, #CUDA streams, and custom operations. Think of those annotations as receipts for code execution on the GPU.
Learn more: zymtrace.com/article/nvtx-zt
Today, we're announcing the General Availability of MIG-aware distributed GPU profiling in zymtrace.
MIG makes shared GPUs more predictable. Zymtrace makes them optimizable.
Zymtrace automatically detects MIG topology and attributes GPU performance metrics to each MIG instance, correlated with full-stack GPU flamegraphs.
zymtrace.com/article/mig
🔊 We’re thrilled to welcome Abdullah Eryuzlu (@KernelNomad_ ) to zymtrace.
Abdullah is a systems engineer with a deep passion for low-level programming, kernels, and performance optimization.
My friends at @zymtrace are looking for Rust engineers 🦀
They're building the platform that makes GPUs go brr — fully remote, early stage, real impact
DM me for an intro, or email team@zymtrace.com
I can vouch that the team is top notch.
Big news: today we are announcing that we have raised $12.2M!
We are building an agentic, profile-guided opt platform that continuously profiles execution from CPU code to CUDA kernels in production to help teams maximize throughput per GPU.
zymtrace.com/article/zymtrac…