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

47 commits

Author SHA1 Message Date
Guillaume Wenzek
4707e58774
zml.Compiler: allow to propagate tensor store names (#1018)
The name can appear in the IR and thanks to #1003 it shows in the web
view of the model making all compute blocks pretty obvious.

The screenshot below without names would be quite confusing, 
but now we can see this is the QKV of first layer of a Llama model.
<img width="2211" height="1208" alt="image"
src="https://github.com/user-attachments/assets/1917edb0-a772-4a1d-9aa7-ad5aaf7b5260"
/>
2026-11-04 16:04:17 +01:00
Hugo Mano
4c355c61b7
zml/sharding: keep unconstrained graph results open (#1004)
Ordinary graph results should have an unspecified layout until
constrained or inferred by the partitioner.

Previously, we could report replication simply because a tensor had no
mesh, even when its stored partition specs were open. Other paths
preserved selected operations’ sharding metadata, making the frontend’s
interpretation depend on how a tensor was produced.

This change gives those results a consistent open state while requiring
concrete layouts at executable boundaries.

Shardy explicitly defines the intended semantics: [“no sharding
attribute on a tensor is equivalent to a fully open tensor
sharding.”](https://openxla.org/shardy/sharding_representation#open)

Open dimensions remain available for further partitioning; closed
dimensions fix the specified layout.
Replication is therefore a constraint, whereas an open layout lets the
partitioner choose either sharding or replication:

This distinction also applies to unused mesh axes. Marking an axis
explicitly replicated prevents propagation from using it, even when a
tensor dimension is open. For example, `[{?}, {}]` must leave unused
axes available; adding replicated={"data", "model"} removes those
choices.

Keeping intermediates open lets the partitioner use constraints from
producers and consumers, with operation-specific rules for
transformations such as dot and reshape.
2026-11-03 18:11:15 +01:00
Guillaume Wenzek
a7a4fcd3f8
zml/sharding: use logical meshes (#943)
## Motivation

This is the big sharding rewrite we need to achieve complex sharding.

Currently we always resolve a mesh logical axis to a mesh physical axis
(or several of them).
But on GPU we always have 1D topology, so we can't have 2D logical
meshes.
So this PR drops the logical -> physical axis bindings, and instead
store a logical -> devices binding.
This is more flexible, and has the nice side effect of simplifying
`Buffer.from`

On stablehlo side this changes how we generate the MLIR because we now
use logical meshes, and `manualComputation` uses logical axes.
(In shardy, GSPM is not affected AFAICT because it uses device ID
directly)

## Buffer.from

This also accelerates `Buffer.from` that I rewrote to be FAST.
Version | Fixed cost | Per device
-- | -- | --
origin/master | 109.6 ns | 35.39 ns
Rewrite | 35.8 ns | 4.38 ns
Improvement | 3.1× | 8.1×

## Creating mesh

I'm adding a new syntax to create LogicalMesh, to allow the more complex
meshes we want to do, and in particular, I now allow to force a specific
number of dimensions.
You can see it in action in `mnist.zig`. 

```
const dp_mp = try platform.registerMesh("DP-MP", try .init(
        .{ .data, .model },
        &.{ .low_bandwidth, .high_bandwidth },
        &.{ 2, -1 },
    ));
 
info: topology used: Mesh(name=DP-MP, partitions=4, replicas=1)
┌ Mappings (logical coordinates from physical coordinates):
├── data (low_bandwidth) -> (bus / 2)
└── model (high_bandwidth) -> (bus % 2)

┌ PhysicalMesh(platform=cpu shardable_axes={ .bus } num_devices=4)
└── [bus] 0..4 (tree)
    ├── Device(id=0, coords={ 0 })
    ├── Device(id=1, coords={ 1 })
    ├── Device(id=2, coords={ 2 })
    └── Device(id=3, coords={ 3 })

┌ Logical coordinates:
└── data=0
    └── model=0,1 -> devices=0,1
└── data=1
    └── model=0,1 -> devices=2,3
```

The previous syntax is still available, and ZML will align logical axes
to physical axes like we do before this PR.
This part as unit tests, and I checked it work as I expect on CUDA but I
would need to double check the logics still works on TPU/Neuron, because
there is a few platform specific branches in that code.

## Test plan

As part of the benchmark Codex generated a test suite with hard-coded
offsets, allowing to check that Buffer.from didn't change behavior
through the commits, checking we correctly compute each individual
shard.

TODO check that LLMD perf isn't degraded.
2026-10-16 15:27:30 +02:00
Guillaume Wenzek
b2f0e03043
zml/Tensor: explicit sharding in Tensor code (#868)
In Buffer code we already have explicit sharding, but not for tensor.

I'm adding a `zml.Sharding` to `.withPartitioning` to make it explicit
which mesh we are working with.
To simplify the migration, `.withPartitioning` in Tensor code can use
`.model` syntax to lookup a sharding by name.
This replace the previous logic of `selectSharding(shape)` which would
look up a sharding that matches the axes of the given partitioning which
could yield surprising behavior.

This also modifies how sharding are stored in zml.Shape.
Before it was storing a list of axis names + a tag (2 * 8 * 64bits), now
I'm storing a zml.Sharding (64 bits) and a compact PartitionArray (32
bits) that references the logical axis of the sharding by offset instead
of by name.

There is an impact on the `TensorRegistry` because it also needs to be
aware of the possible shardings, instead of delegating the matching
partition spec -> sharding to loading. This means error will be detected
sooner.

`store.createTensor` accepts `@enumLiteral()` to lookup the relevant
sharding.

This also simplifies `zml.Buffer` because the full sharding is now
stored in the shape, so it doesn't need to be passed independently. It
also means that it will propagate from the tensor who are graph inputs,
to the buffers that are eg inputs.

`Placement` logic also got a bit simpler.
2026-10-06 15:37:22 +02:00
Benjamin Rabier
af4e079f34
zml/exe: callOpts/zml.testing.autoCall replaced by eval + remove run|callOpts (#897)
Removing callOpts & runOpts to simplify the API and changing `io` to be
required for API clarity. I'm replacing `zml.testing.autoCall` with
`Exe.eval` which solves most needs in a simpler way IMHO
2026-10-05 13:51:36 +02:00
Raphael Nahoum
3178484b27
zml/io: record computed bindings in the store (#749)
A binding created through `maybeCreateBinding` is computed from its
sources by an executable and must never be streamed from the checkpoint.
`Loader.defaultCallback` inferred that from `sources.len != 1`, which a
single-source binding fails resulting to the raw bytes being loaded and
producing wrong results
2026-09-02 12:51:09 +02:00
Corentin Godeau
577d6452bf
zml/io: rework zml.io.load (#586)
The old `zml.io.load` was plagued with problems. This PR is an attempt
at improving the state of things.

One major problem of `zml.io.load` was that it was not very composable.
It was either using it to load all the model or doing everything by
hand.

Another problem was that it didn't offer a way to apply transformations
at load time to the tensors stored in a safetensors file. For example,
it happens that for MoE models, instead of the experts weights to be
tightly packed in a nice 3D tensor, the weight file contain one tensor
for each expert. This is nice until your implementation required a 3D
tensor as input. Using the old `zml.io.load` API this resulted in very
convoluted way to do concatenation at load time. With this new API, we
offer convenience so that it can be handled nicely and as fast as
possible.

The main change is the introduction of the `Loader` struct. It's a
struct that you instantiate once and reuse whenever you want to load
tensors. It relies on `Binding`, which are a way to store which tensor
are required and how they need to be combined (if it's a complex binding
involving more than one source tensor).

One advantage of this `Loader` is that it's composable. Loading a struct
using `Loader.auto(Struct)` or loading each individual field of `Struct`
has essentially the same behavior. This solved the major problem of the
old solution.

For simplicity I kept the old model loading code almost identical, as
this new solution is a drop-in replacement.

# Update

After some discussions with @gwenzek I've changed my mind. Instead of
having a declarative API, we'll provide helper to do transformation
easily. The main changes that this PR now bring are:
* Introduce `Loader` struct
* `Loader` exposes `load` which is the composable replacement of
`zml.io.load`
* `Loader` exposes `loadExecute` that allows you to execute an
executable with the buffers loaded from the sources associated with a
tensor. This allows for example to concatenate tensors.

We'll continue to work on it, this is just a preliminary work that
allows us to do transformation at load time in LLMD.
2026-07-17 18:41:18 +02:00
Guillaume Wenzek
0979289ffe
zml/sharding: pass sharding by pointer and simplify replicated usage (#514)
This PR simplifies the common replicated case while making sharding
intent explicit and use sharding by pointer ( sharding struct is quite
big: ~600 bytes).

Using pointers for shardings also avoids unnecessary sharding copies and
makes it easier to share stable sharding instances across compilation,
loading, and runtime paths.

- `Platform` owns the canonical replicated sharding
- `Buffer` APIs now take explicit sharding specs:
    - `.replicated`
    - `.{ .sharded = sharding_ptr }`
- `createTensor` / `maybeCreateTensor `now require explicit partitioning
instead of accepting null
- compilation/loading now use pointer-based sharding lists

This makes simple cases like mnist and benchmark much cleaner: callers
no longer need to manually construct and thread a replicated sharding
just to use the default case, but they still state placement explicitly
at the call site.

---------

Co-authored-by: Hugo Mano <hugo@zml.ai>
2026-05-06 12:46:15 +02:00
Hugo Mano
8b12d2ef1e
bazel: make repo-wide cquery work across host and linux target analysis (#465)
This PR fixes several Bazel analysis regressions so both of these
commands work reliably:

- `bazel cquery //...`
- `bazel cquery --platforms=@zml//platforms:linux_amd64 //...`

After recent changes and the rebase, repo-wide cquery was failing for
three separate reasons:

- ZLS toolchains were over-constrained by target platform: updated ZLS
toolchain registration to constrain only the exec platform.
This avoids cross-target analysis failures when host-side completion
tooling is analyzed under a foreign target platform.
- OCI packaging targets were analyzed on host platforms where their base
images do not apply: marked Linux OCI image targets as Linux x86_64
compatible only. Also switched the Debian base image pull from Docker
Hub to the GCR mirror to avoid CI fetch failures when resolving
packaging images manifests due to rate limiting
- Triton Python deps were fetched for the host Python platform instead
of the Linux wheel platform the lockfile was generated for: restored
Linux x86_64 wheel resolution for `triton_py_deps` in `MODULE.bazel`.
This prevents macOS host analysis from attempting to fetch a
`triton==3.6.0` wheel for an unsupported host platform.


Also added a step in ci to prevent regression
2026-04-17 11:48:09 +02:00
Corentin Godeau
ac9bc32d89
zml/attention: add Triton Unified Attention backend (#417)
This PR introduces a Triton paged attention backend, unlocking ROCm
support.

It relies on a Python sandbox to generate the TTIR.

The major change is that the KVCache now needs to be per-layer for paged
attention. The `layer_index` is now superfluous and will probably be
removed in the future.
2026-04-13 11:39:08 +02:00
Benjamin Rabier
c3c0a69689
ci: update actions (#447)
- Update setup-bazel & checkout to latest
- Add a bunch of `tags = ["manual"]` for docker image related targets
2026-04-01 10:48:10 +02:00
Corentin Godeau
2eb8423e8a
Update doc for V2 (#428) 2026-03-24 17:00:10 +01:00
Corentin Godeau
70e4c9953d
Bump zig to 0.16.0-dev.2722+f16eb18ce (#409)
Co-authored-by: Hugo Mano <hugo@zml.ai>
2026-03-10 15:58:48 +01:00
Hugo Mano
abde0a04dd
zml: sharding (#407)
Co-authored-by: Benjamin Rabier <benjamin@zml.ai>
2026-03-10 11:17:57 +01:00
Steeve Morin
dcbf5f2e27 workspace: update to 0.16.0-dev.2611+f996d2866, add remote exec
also:
- use toolchains_llvm_bootstrapped for macOS builds
2026-02-16 12:05:01 +01:00
Steeve Morin
0f460fb636 zml: expose Memory, pass Platform as *const, add zml.io.load 2026-02-03 10:59:39 +00:00
Steeve Morin
21a7c5fec8 platforms: pass allocator to load 2026-01-19 17:41:57 +01:00
Hugo Mano
25a5ee10f6 rework zml.io.* 2026-01-14 18:04:55 +01:00
Steeve Morin
dc4f6e2f00 zml: remove zml.init and deinit 2026-01-11 21:24:57 +01:00
Steeve Morin
2ba6d73af2 zml: expose stdx from inside zml 2026-01-06 10:52:28 +00:00
Steeve Morin
c2780ca7c5 workspace: zml2 -> zml 2026-01-06 10:08:17 +00:00
Steeve Morin
48eddd98b6 examples/mnist: cosmetic changes 2026-01-05 09:09:43 +00:00
Steeve Morin
7cdce4ffae zml/platform: new compile prototype 2026-01-03 10:36:44 +00:00
Steeve Morin
f3245c5968 MNIST running again 2026-01-01 17:56:29 +00:00
Corentin Godeau
11ca632931 Introduced variant of Exe.call
By default, we don't wait for execution completion when calling
`Exe.call`. If you want to await the result, you can use `Exe.callOpts`.
2025-12-22 15:18:16 +01:00
Corentin Godeau
2739c925a6 Fixed mnist example with new VFS.File changes 2025-12-22 12:13:58 +01:00
Hugo Mano
860a52e8f0
io: fixes (#366) 2025-12-17 16:34:59 +01:00
Corentin Godeau
95401d52aa wip llama 2025-12-16 17:58:33 +01:00
Corentin Godeau
f680e17178 First clean version of Mnist 2025-12-15 18:55:43 +01:00
Corentin Godeau
6df392bbe2 First port of Mnist to new API
Everything is done by hand so that's not the final version, but at least
it works!
2025-12-15 16:10:50 +01:00
Corentin Kerisit
f1dce257fe
all: provide -fllvm to all targets that requires it (#348)
Until zig x86 backend is fixed.
2025-10-17 19:05:29 +02:00
Corentin Kerisit
36d583dd58
workspace: use upstreamed rules_zig instead of our fork (#340)
This PR uses the new release of rules_zig where we upstreamed all the
work from the zml rules_zig fork.

Not much changes from the POV of the public API except for `copts`
becoming `zigopts`.

Also, the global `c` module is only available to Zig modules that depend
on a non empty `cc_library`.
This is behavior that can probably be modified in `rules_zig` later on.

Finally, ZLS support had to be completely rethought to comply with the
change in shape of ZigModuleInfo providers and subsequent rules.

This PR is blocked until `rules_zig` exposes `ZigModuleInfo` for
`zig_binaries`.
2025-10-13 14:34:33 +02:00
Guillaume Wenzek
0312d6f678
zml: gather (#330)
Revamp the `gather` api to match `scatter`

(prerequesite of #329 )

## Gather new api

Now the syntax is to give a named list of indices. Each name must
correspond to one axis in the gathered tensor.
This match `scatter`, and avoid the user to have to concatenate indices
in the same order than the input axes,
which is error prone cause any screw up will compile but index at the
wrong offsets.

For 1 axis it doesn't change much: 

```
// before
self.weight.withTags(.{ .voc, .d }).gather(.{.voc}, .{ idx }, .{});
// after
self.weight.withTags(.{ .voc, .d }).gather(.{ .voc = idx }, .{});
```

But for two it helps a lot:

```
// before
self.weight.withTags(.{ .voc, .d }).gather(.{.voc, .d}, .{ .concatenate(&.{idx_voc, idx_d}, .last)}, .{});
// after
self.weight.withTags(.{ .voc, .d }).gather(.{ .voc = idx_voc, .d = idx_d }, .{});
```

Also adds a `gather_` that offers the same apis but with axis position
instead of names.
This one is more suitable inside library functions when dealing with
unknown names, making it complicated to create the "indices" struct.
I think we could generalize this pattern of offering "non-tagged" api
with an underscore suffix, simplifying the job of LSP.

## topk new API

I realized that most of the code calling topk was renaming the output
axis.
The idea is that logprob.topk(.voc) doesn't return you a tensor with voc
entry but only top_voc entries.
For the values it doesn't make much a difference but for the indices
it's embarrassing and it break usages of gather/scatter.

Now the user of `topK` can either use the unnamed api and pass a number,
of if using the name api must give a new name for the indexed axis.

## Yarn

Support Yarn rope embeddings. It's equivalent to the "llama3" embedding
except they do the interpolation in time space instead of freq space.
2025-09-25 12:29:46 +02:00
Guillaume Wenzek
df77b33d8e
async: remove asynk, asyncc, awaitt, await_ (#325) 2025-09-18 10:05:54 +02:00
Steeve Morin
56ac3e27dd
zml: remove gguf and torch loaders (#317)
Torch loader might be reintroduced later, if the need arises.
2025-08-27 09:43:39 +02:00
Steeve Morin
24575c2232
workspace: switch from zig_cc_binary to zig_binary (#311)
Following the rules_zig bump that adds the `linkmode` setting, we can
use the C linker directly.

We can now remove the `zig_cc_binary` hack.
2025-08-21 13:12:15 +02:00
Steeve Morin
3b81c5630e
zml: remove examples workspace (#308)
Closes #302
2025-08-19 19:42:50 +02:00
Corentin Godeau
f323979cb2
zml/buffer: various improvements (#248)
* `Buffer.from` is blocking by default
* `Buffer.from` takes options to control the loading This includes
awaiting for the buffer or to which memory the buffer is copied
2025-06-06 18:12:49 +02:00
Hugo Mano
2fd9516773
workspace: query, build and test (#187)
Ensure that our Bazel setup for the framework and examples work through
queries, builds and tests.
Also fix broken code and deps in the codebase.

As of today only Neuron is broken (cf:
https://github.com/zml/zml/pull/111)
2025-02-12 10:40:20 +01:00
Steeve Morin
d76e5b9cd4
examples: fix logFn usages (#167)
Ooops! Forgot to update the examples.
2025-01-24 21:07:36 +01:00
Guillaume Wenzek
424bbc5dcb
zml: improve source locations (#148)
Put the name of the operator in the source location.
This seemed redundant at first because it's not needed when looking at
the stablehlo,
but it's nice to have it to understand the optimization passes.

I'm also including a few QoL:

* sdpa don't need a bias argument, attn_mask already play this role.
* gatherSlices should accept a shape literal `.{ .a = 5, .b = 128 }`
* Shape.outer to combine two shapes into the superset of their axes
* Tensor.all (since we already have Tensor.any)
* argMax doesn't need to specify the dtype, it can be inferred from the
size of the input tensors. If the user care about the dtype they can
manually convert.

This PR is stacked on top of #147
2025-01-09 17:18:20 +01:00
Guillaume Wenzek
e8fa410537
pjrt/zml: expose client creation flags (#129)
The Pjrt api allows to passe string flags to the plugin on client
creation.
Since we don't like working with strings I've converted the strings
supported by the cuda plugin into a struct.
For now I've focused on the strings corresponding to the allocator
settings following #125 

More settings are not exposed ATM, will follow up with #132 

3d31c48c71/xla/pjrt/c/pjrt_c_api_gpu_internal.cc (L76-L86)

AFAICT the cpu plugin doesn't read flags at all.
Neuron doesn't have known flags, TPU requires more investigation.

**Breaking change**: `context.autoPlatform()` ->
`context.autoPlatform(.{})`
2024-12-11 13:38:04 +01:00
Guillaume Wenzek
d669bdc6bf
zml: cleanup module.zig (#115)
* compileInternal now works with function not with "module"
* BaseExe now allocates all the memory needed to call `pjrtExecute`
* `Exe` is the type variant of `BaseExe` and enforce the right Zig arg
are passed to `call`. `exe.prepare(model)` don't need to allocate
anymore, the allocation happened during compilation.
* public entry points like `compile`, `compileModel`, `compileFn` are
now at the top of the file
* the caching logic has been mostly inlined inside `compileInternal`
* `compile`, `compileFn`, `Exe`, `BaseExe` which are the user visible
API have been moved to `exe.zig`
* `CompilationContext` and all the compilation logic stays in
`module.zig`
2024-12-05 17:33:19 +01:00
Steeve Morin
db88158518
async: rework async runtime to use coroutines and cross thread signaling (#100)
This mostly reworks the runtime to enable proper cross thread signaling
for `callBlocking`.

API changes include:
- `async_ -> asyncc`
- `await_ -> awaitt`
- proper type inference for non generic arguments even for generic
functions
- bump `libxev`
- use `epoll` on linux by default (can be comptime overridden through
`xev_options.linux_backend` in the root module)

Mostly, also, it's pretty fast.
2024-11-22 17:56:22 +01:00
Steeve Morin
783a3cdeb8
zml: add stdx, rework async signature inference (#89)
This one is a chonky.

This commit adds a new `stdx` module with a few utility functions. It is
very far reaching. Forgive the size.

Also, clean the logs in the executables.
2024-11-15 17:12:07 +01:00
Steeve Morin
ccd925309b
async: rename async_ to asyncc and add Generic slugs (#71)
`asyncc` is arguably nicer to write than `async_`, so use that.

Also, add an explicit `Generic` version that can work with `anytype`
functions (but on which type inference will be disabled).
2024-11-01 17:36:08 +01:00
Steeve Morin
13d84615bb zml: initial release 2024-09-17 11:11:18 +02:00