smit 5b1b3c51d4 language_models: Fix high memory consumption while using Agent Panel (#35764)
Closes #31108

The `num_tokens_from_messages` method we use from `tiktoken-rs` creates
new BPE every time that method is called. This creation of BPE is
expensive as well as has some underlying issue that keeps memory from
releasing once the method is finished, specifically noticeable on Linux.
This leads to a gradual increase in memory every time that method is
called in my case around +50MB on each call. We call this method with
debounce every time user types in Agent Panel to calculate tokens. This
can add up really fast.

This PR lands quick fix, while I/maintainers figure out underlying
issue. See upstream discussion:
https://github.com/zurawiki/tiktoken-rs/issues/39.

Here on fork https://github.com/zed-industries/tiktoken-rs/pull/1,
instead of creating BPE instances every time that method is called, we
use singleton BPE instances instead. So, whatever memory it is holding
on to, at least that is only once per model.

Before: Increase of 700MB+ on extensive use

On init:
<img width="500" alt="prev-init"
src="https://github.com/user-attachments/assets/70da7c44-60cb-477b-84aa-7dd579baa3da"
/>
First message:
<img width="500" alt="prev-first-call"
src="https://github.com/user-attachments/assets/599ffc48-3ad3-4729-b94c-6d88493afdbf"
/>
Extensive use:
<img width="500" alt="prev-extensive-use"
src="https://github.com/user-attachments/assets/e0e6b688-6412-486d-8b2e-7216c6b62470"
/>

After: Increase of 50MB+ on extensive use
On init:
<img width="500" alt="now-init"
src="https://github.com/user-attachments/assets/11a2cd9c-20b0-47ae-be02-07ff876e68ad"
/>
First message:
<img width="500" alt="now-first-call"
src="https://github.com/user-attachments/assets/ef505f8d-cd31-49cd-b6bb-7da3f0838fa7"
/>
Extensive use: 
<img width="500" alt="now-extensive-use"
src="https://github.com/user-attachments/assets/513cb85a-a00b-4f11-8666-69103a9eb2b8"
/>

Release Notes:

- Fixed issue where Agent Panel would cause high memory consumption over
prolonged use.
2025-08-07 11:39:27 +05:30
2025-07-09 08:57:03 +08:00
2025-08-05 12:56:49 +00:00
2025-06-06 09:39:35 +00:00
2025-05-17 12:34:42 +00:00
2025-04-24 21:29:33 +00:00
WIP
2023-12-14 09:25:14 -07:00
2025-03-10 01:06:11 -07:00
2024-09-30 17:46:21 -04:00
2025-02-04 09:02:59 -05:00
2025-02-04 09:02:59 -05:00
2024-08-08 17:21:38 -07:00
2025-07-29 14:24:10 -04:00
2025-03-10 01:06:11 -07:00

Zed

Zed CI

Welcome to Zed, a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.


Installation

On macOS and Linux you can download Zed directly or install Zed via your local package manager.

Other platforms are not yet available:

Developing Zed

Contributing

See CONTRIBUTING.md for ways you can contribute to Zed.

Also... we're hiring! Check out our jobs page for open roles.

Licensing

License information for third party dependencies must be correctly provided for CI to pass.

We use cargo-about to automatically comply with open source licenses. If CI is failing, check the following:

  • Is it showing a no license specified error for a crate you've created? If so, add publish = false under [package] in your crate's Cargo.toml.
  • Is the error failed to satisfy license requirements for a dependency? If so, first determine what license the project has and whether this system is sufficient to comply with this license's requirements. If you're unsure, ask a lawyer. Once you've verified that this system is acceptable add the license's SPDX identifier to the accepted array in script/licenses/zed-licenses.toml.
  • Is cargo-about unable to find the license for a dependency? If so, add a clarification field at the end of script/licenses/zed-licenses.toml, as specified in the cargo-about book.
S
Description
GPUI – Community Edition maintained by Oak Team
https://gpui-ce.github.io/
Readme
257 MiB
Languages
Rust 95.5%
WGSL 1.2%
Metal 1.1%
HLSL 1.1%
Python 0.7%
Other 0.3%