0
Fork 0
mirror of https://github.com/zml/zml.git synced 2026-11-16 19:11:09 +00:00
Commit graph

2 commits

Author SHA1 Message Date
Corentin Godeau
51db372455
third_party/iree: bump iree tokenizer to 4d4e97d00f099a21f38eeff26f82a6d9e3643a11 (#624) 2026-07-02 15:46:02 +02:00
Benjamin Rabier
448084908a
zml/tokenizer: add IREE tokenizer (#416)
Adding the [IREE
tokenizer](https://github.com/iree-org/iree/blob/main/runtime/src/iree/tokenizer/README.md).Being
made from the ground up with streaming (de-)tokenization in mind, I've
extended the APIs to expose a `std.Io.Writer` for the tokenization.

I've quickly benchmarked IREE's tokenizer vs HuggingFace's one with a
request I retrieved from a coding agent (opencode) in the middle of a
session. The request body was 360KB encoded in 95K tokens. I also did
another test with a similarly sized request with the same results as
shown hereafter.

I've tested two cases:

- oneshot: the template is rendered all at once and only then we encode
the whole string.
- stream: the template rendering and encoding are pipelined to avoid the
intermediate allocation.

There is a slight difference in the generated tokens between HuggingFace
and IREE. Some tokens like `introdu` were encoded as `i`, `n`, `t`, etc.
Decoding them returns the same text. It's very close in terms of total
token count:

- hf: 95779
- iree/stream: 95705
- iree/oneshot: 95587

| Model | IREE avg (oneshot / stream) ms | HuggingFace avg (ms) | Uplift
vs HF (oneshot / stream) |
|---|---:|---:|---|
| liquidai/LFM2.5-1.2B-Instruct | 8.5 / 7.3 | 40.5 | 4.8x / 5.5x |
| Qwen/Qwen3.5-9B | 6.0 / 8.2 | 59.4 | 9.9x / 7.2x |
| mistralai/Ministral-3-3B-Reasoning-2512 | 7.4 / 6.9 | 59.2 | 8x / 8.6x
|


It's unclear why the Qwen's chat template is somehow slower in the
stream case, maybe because there are more writes. Adding non-empty
buffer in the interface helps a bit, but tends to slow down mistral
case. So well

---------

Co-authored-by: Corentin Kerisit <corentin.kerisit@gmail.com>
2026-04-07 16:42:55 +02:00