zymtrace

Powering Efficient AI: A continuous profiling platform for CPU and GPU workloads, that provides actionable insights to optimize perf & debug faster

[OpenObservability @OpenObserv]

📢 May episode is out! 📢
OpenTelemetry Comes of Age: CNCF Graduation, Profiling and eBPF

With @horovits hosting @israel_ogbole, CEO & Co-founder @zymtrace, OTel Profiling SIG member.

🎧 https://t.co/s487tVy6iO
📺 https://t.co/N4RknpOyrf

recap post:
👉 https://t.co/euLyVRXXcC

[zymtrace @zymtrace]

Zymtrace automatically detects MIG topology and attributes GPU performance metrics to each MIG instance, correlated with full-stack GPU flamegraphs.

https://t.co/fd23FNOF5w

[zymtrace @zymtrace]

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 @zymtrace]

🦀 He has also been building a POSIX-compatible kernel in Rust targeting RISC-V.

Excited for what we’ll build together 🚀

[zymtrace @zymtrace]

🔊 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.

[zymtrace @zymtrace]

Join @zymtrace and help us design agentic workflows and user experiences to optimize AI workloads.

https://t.co/7d7ER02BDs

[zymtrace @zymtrace]

👉 Learn more about Tim’s background and why he joined @zymtrace here:

https://t.co/vfZG7DqscU

[zymtrace @zymtrace]

🔊 We are thrilled to welcome Tim to the team!

Tim is a Rust enthusiast focused on low-level systems and kernel development

We are hiring!

[zymtrace @zymtrace]

@halvarflake Thanks @halvarflake. We’ve got a few roles up (https://t.co/O651iZnQLD), but if you’re great with Rust, don’t wait for a perfect listing — just send your application in.

[Halvar Flake @halvarflake]

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 [email protected]

I can vouch that the team is top notch.

[zymtrace @zymtrace]

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.

https://t.co/v1nHuTgWmS

[zymtrace @zymtrace]

AI clusters lose enormous amounts of compute to hidden bottlenecks that most teams simply cannot see. We make them visible.

We're grateful to our customers and investors for their trust!

[zymtrace @zymtrace]

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.

https://t.co/v1nHuTgWmS

[Tanel Poder 🇺🇦 @TanelPoder]

The @zymtrace folks are going *really deep* into what your GPUs are actually doing (and waiting for) when you're running your most expensive workloads... 🤓

[Halvar Flake @halvarflake]

The @zymtrace folks are killing it - this article is really quite a great read:

https://t.co/uE56i2J6wi

[zymtrace @zymtrace]

The best part? They're feeding @zymtrace GPU profiles into AI coding agents—automatically creating PRs with performance fixes 🚀

https://t.co/VUgivPxfkP

[zymtrace @zymtrace]

@MeetAnamAI achieved 250% faster inference and 90% higher throughput with $0 spent on new GPUs ⚡

Most teams solve GPU performance by throwing money at more @nvidia GPUs. Anam took the performance optimization approach.

[zymtrace @zymtrace]

👉 Learn more about Matti's background and why he joined zymtrace here:
https://t.co/t6qd4hb0BB

[zymtrace @zymtrace]

🔊 We are thrilled to welcome Matti to the team!

🚀 Before joining @zymtrace , he worked across different areas of software engineering, with a strong focus on low-level systems and kernel development.

[zymtrace @zymtrace]

🚀 Lots of progress with #zymtrace in Sept: GPU + CPU metrics, absolute CPU % mode, Python 3.13+ support, Zing unwinding & major performance improvements.
Also contributing Python unwinding improvements to the upstream OTel eBPF profiler 👉 PR #837
https://t.co/gDkY7u9mNH