Gluon: a GPU Programming Language Based on the Same Compiler Stack as Triton

Posted4 months agoActive4 months ago

matt_d

83 points

24 comments

github.comTechstory

calmmixed

Debate

60/100

GPU ProgrammingTritonGluonCuda

Key topics

GPU Programming

Triton

Gluon

Cuda

Gluon is a new GPU programming language based on the same compiler stack as Triton, sparking discussion about its design and potential competition with NVIDIA's CUDA and other similar projects.

Snapshot generated from the HN discussion

Discussion Activity

Light discussion

First comment

14m

Peak period

3-4h

Avg / period

Comment distribution24 data points

Loading chart...

Based on 24 loaded comments

Key moments

01Story posted
Sep 17, 2025 at 3:50 PM EDT
4 months ago
Step 01
02First comment
Sep 17, 2025 at 4:04 PM EDT
14m after posting
Step 02
03Peak activity
5 comments in 3-4h
Hottest window of the conversation
Step 03
04Latest activity
Sep 18, 2025 at 7:03 AM EDT
4 months ago
Step 04

Generating AI Summary...

Analyzing up to 500 comments to identify key contributors and discussion patterns

Discussion (24 comments)

Showing 24 comments

ronsor

4 months ago

3 replies

The fact that the "language" is still Python code which has to be traced in some way is a bit off-putting. It feels a bit hacky. I'd rather a separate compiler, honestly.

derbOac

4 months ago

1 reply

Yeah that struck me as odd. It's more like a Python library or something.

zer0zzz

4 months ago

It’s a dsl not a library. The kernel launch parameters and the ast walk generate ir from the Python.

JonChesterfield

4 months ago

1 reply

Mojo for python syntax without the ast walking decorator, cuda for c++ syntax over controlling the machine, ah hoc code generators writing mlir for data driven parametric approaches. The design space is filling out over time.

pizlonator

4 months ago

1 reply

The fact that these are all add on syntaxes is strange. I have my ideas about why (like you want to write code that cooperates with host code).

Do any of y’all have clear ideas about why it is that way? Why not have a really great bespoke language?

saagarjha

4 months ago

1 reply

Hard to beat trifecta of familiar language, same source files and toolchain, JIT compiled

pizlonator

4 months ago

1 reply

That’s sort of what I assumed, yeah. And I think that makes sense.

But they end up adding super sophisticated concepts to the familiar language. Makes me wonder if the end result is actually better than having a bespoke language.

saagarjha

4 months ago

I mean you used to be able to write TTGIR directly this is mostly sugar on top of that

zer0zzz

4 months ago

This is pretty common among these ml toolchain, and not a big deal. They use pythons ast lib and the function annotations to implement an ast walker and code generator. It works quite well.

lukax

4 months ago

6 replies

Is this Triton's reply to NVIDIA's tilus[1]. Tilus is suposed to be lower level (e.g. you have control over registers). NVIDIA really does not want the CUDA ecosystem to move to Triton as Triton also supports AMD and other accelerators. So with Gluon you get access to lower level features and you can stay within Triton ecosystem.

[1] https://github.com/NVIDIA/tilus

mdaniel

4 months ago

1 reply

Also it REALLY jams me up that this is a thing, complicating discussions: https://github.com/triton-inference-server/server

robertlagrant

4 months ago

Oh! I thought it was that, having jumped straight to comments before article.

bobmarleybiceps

4 months ago

1 reply

it feels like Nvidia has 30 "tile-based DSLs with python-like syntax for ML kernels" that are in the works lol. I think they are very worried about open source and portable alternatives to cuda.

WithinReason

4 months ago

Not at all, they are the ones pushing for vendor agnostic Tensorcore extensions in Vulkan, which would solve some part of the portability issue: https://github.com/jeffbolznv/vk_cooperative_matrix_perf

YetAnotherNick

4 months ago

No, gluon was in development before Tilus was announced. Could be a response to Cute DSL though.

[1]: https://docs.nvidia.com/cutlass/media/docs/pythonDSL/cute_ds...

saagarjha

4 months ago

I believe it’s the other way around; Gluon exposes the primitives Triton was built on top of.

jillesvangurp

4 months ago

There's a lot of pressure on the CUDA ecosystem at this point:

- most of the trillion dollar companies have their own chips with AI features (Apple, Google, MS, Amazon, etc.). Gpus and AI training are among their biggest incentives. They are super motivated to not donate major chunks of their revenue to nvidia.

- Mac users don't generally use nvidia anymore with their mac hardware and the apple's CPUs are a popular platform for doing stuff with AI.

- AMD, Intel and other manufacturers want in on the action

- The Chinese and others are facing export restrictions for Nvidia's GPUs.

- Platforms like mojo (a natively compiled python with some additional language features for AI) and others are getting traction.

- A lot of the popular AI libraries support things other than Nvidia at this point.

This just adds to that. Nvidia might have to open up CUDA to stay relevant. They do have a performance advantage. But forcing people to chose, inevitably leads to plenty of choice being available to users. And the more users choose differently the less relevant CUDA becomes.

reasonableklout

4 months ago

It sounds like they share that goal. Gluon is a thing because the Triton team realized over the last few months that Blackwell is a significant departure from the Hopper, and achieving >80% SoL kernels is becoming intractable as the triton middle-end simply can't keep up.

Some more info in this issue: https://github.com/triton-lang/triton/issues/7392

ivolimmen

4 months ago

1 reply

Not to be confused with the Gluon UI toolkit for Java : https://gluonhq.com/products/javafx/

liuliu

4 months ago

Or the GluonCV by mxnet guys (ancient! https://github.com/dmlc/gluon-cv)

huevosabio

4 months ago

Not to be confused with gluon the embbedable language in Rust: https://github.com/gluon-lang/gluon

ericdotlee

4 months ago

Why is zog so popular these days? Seems really cool but I have yet to get the buzz / learn it.

Is there a big reason why Triton is considered a "failure"?

xcodevn

4 months ago

Interesting, i can see this being very similar to Nvidia's CUTE DSL. This hints that we are converging to a (local) optimal design for Python-based DSL kernel programming.

some_guy_nobel

4 months ago

Amazon (+ Microsoft) already released a language for ML called gluon 8 years ago: https://aws.amazon.com/blogs/aws/introducing-gluon-a-new-lib...

autogluon is popular as well: https://github.com/autogluon/autogluon

View full discussion on Hacker News

ID: 45280592Type: storyLast synced: 11/20/2025, 1:30:03 PM

Want the full context?

Jump to the original sources

Read the primary article or dive into the live Hacker News thread when you're ready.

Open link View on HN