mirror of
https://github.com/zml/zml.git
synced 2026-11-16 19:11:09 +00:00
docs/learn/loader.md is the guide to zml.io.Loader: the recipe over a
VFS with Remotes, placing tensors on a mesh or in host memory,
composite tensors built from Source's shape ops, programs bound with
bindProgram, and what each handle borrows and how a load fails. The
errors get a short summary that points at Loader's doc comment, which
holds the contract. The docs index, the README's taste of ZML,
Buffer's doc and the headers of zml/io.zig and zml/io/loader.zig link
it.
write_first_model gains a last step, 'Loading weights': a few lines of
Python write the layer's weight and bias to a .safetensors file, the
layer binds them through a TensorStore view, and main loads them over
a VFS with Remotes through the loader before calling the executable.
The TensorStore paragraph now says the store holds the shapes and the
loader fills the buffers.
zml.io.next goes: nothing in zml or llmd names it any more.
The tutorial's program and every snippet of the guide were built and run
on 4 CPU devices from a scratch target that is not committed: the
tutorial prints {6,11,16} from the Python-written checkpoint, and the
placement (host_mapped included) and composite snippets load the values
they describe. The program snippet stands alone: it defines its sources
and its forward dequantizes by block and places its result as the output
is, without which the load fails with InvalidBinding; on an 8x256 weight
with one scale per row and 128 columns it loads every value as expected,
row-sharded.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
History
|
|
|---|---|---|
| .. | ||
| howtos | ||
| learn | ||
| misc | ||
| tutorials | ||
| README.md | ||
Greetings, Programs!
If you want to run our example models, please head over to Getting Started.
Ready to write some code? Try starting with your first model in ZML, or familiarize yourself with the high-level ZML concepts first.
MENU:
Tutorials
- Getting Started : install ZML, run LLama
- Writing your first model
- Simplifying Dimension Handling - Tagged Tensors!
How to ?
- HuggingFace Authentication
- Port Pytorch models to ZML
- Cross Compile and Deploy Models on a Server
- Dockerize Models
- Profile ZML Programs
Learn more...
- ZML Concepts : Tensors, Models, Executables, etc. explained
- Loading checkpoints : The loading recipe, placement, programs, lifetimes and errors