|
|
4294a4d08f
|
Bump hftokenizers dependency versions in Bazel and Cargo lockfiles (MODULE.bazel.lock, Cargo.toml, Cargo.lock)
|
2025-04-04 12:54:33 +00:00 |
|
|
|
78d7b672e7
|
runtimes/cpu: sandbox CPU PJRT plugin, simplifying as there are no additional NEEDED dependencies.
|
2025-04-03 11:57:46 +00:00 |
|
|
|
2d321d232d
|
runtimes/cuda: sandbox CUDA dependencies by removing them from the leaf binary, sandboxing the dependency graph, marking dlopen direct dependencies as NEEDED, setting RPATH to the sandbox, loading the PJRT plugin from the sandbox, and enabling weak CUDA symbols without direct linking.
|
2025-03-26 11:18:29 +00:00 |
|
|
|
a5420068b1
|
pjrt: emit warning instead of panic when FFI Extension is missing (e.g., on TPU).
|
2025-03-24 09:40:44 +00:00 |
|
|
|
dc121fce4f
|
Update example MODULE.bazel and lockfile to reflect toolchains_llvm_bootstrapped bump to 0.2.4.
|
2025-03-20 12:17:30 +00:00 |
|
|
|
907577525f
|
Update MODULE.bazel and lockfile to bump toolchains_llvm_bootstrapped to version 0.2.4.
|
2025-03-18 11:47:22 +00:00 |
|
|
|
f27a524f31
|
Update rules_zig: add zig_srcs target, fix source handling bug, clean up BUILD files, adjust async/coro.zig tests, and disable nemo and yaml model loaders.
|
2025-03-13 12:27:21 +00:00 |
|
|
|
6fc1148206
|
async/coro: make coroutines unwindable by zeroing the initial stack region, preventing random unwinding behavior and SIGSEGV during _Unwind_Backtrace.
|
2025-03-10 16:25:45 +00:00 |
|
|
|
f63c673f45
|
bazel: add RPATH manipulation to patchelf
|
2025-03-05 11:56:40 +00:00 |
|
|
|
9488672d4b
|
workspace: bump xla to version 20250710.0-22ea002
Also:
- Bump XLA deps : `com_github_grpc_grpc` and `com_google_protobuf`
- Inject `rules_ml_toolchain`
- Fix `zig_proto_library` rule
|
2025-03-04 17:12:34 +00:00 |
|
|
|
fa0ed045ef
|
runtimes/cuda: downgrade cuda and cudnn
This commit reverts part of https://github.com/zml/zml/pull/238/files
This is required because XLA has a strong dependencies on CUDA 12.8 and
upgrading to 12.9 is impossible due to
https://github.com/NVIDIA/cccl/issues/4967
|
2025-02-28 17:36:12 +00:00 |
|
|
|
ff1433d998
|
pjrt: bind PJRT_Client_CreateUninitializedBuffer.
|
2025-02-25 10:37:45 +00:00 |
|
|
|
8456a0d073
|
zml/pjrt: add binding for PJRT_Device_MemoryStats.
|
2025-02-19 12:14:05 +00:00 |
|
|
|
a580f2a398
|
Async: use stronger memory ordering to prevent potential segfaults due to ordering issues.
|
2025-02-18 11:38:56 +00:00 |
|
|
|
4d6d975dc0
|
Patch aio.zig: update loadBuffersWithPrefix argument type to match the conditional type of loadBuffers init_args.
|
2025-02-13 09:48:13 +00:00 |
|
|
|
af8844c1f1
|
Add model prefix support when loading a model from safetensors, enabling use of a specific model prefix (e.g., ModernBertModel) instead of the full model. Tested with the text embeddings server project.
|
2025-02-12 13:18:27 +00:00 |
|
|
|
1cafcc3c60
|
Workspace: bump XLA to newer version.
|
2025-02-05 17:35:27 +00:00 |
|
|
|
9ef838be25
|
Update neuron runtime BUILD.bazel to use Bazel manual tag and S3 cache integration.
|
2025-02-03 14:03:33 +00:00 |
|
|
|
dd52e988b4
|
Update example Bazel build files (MODULE.bazel, llama, modernbert) to test the revamped commit workflow.
|
2025-01-31 16:28:38 +00:00 |
|
|
|
0a2ab7c8cb
|
Remove usingnamespace from MLIR.
|
2025-01-28 09:35:58 +00:00 |
|
|
|
f8ab0d7b2a
|
Remove dead imports.
|
2025-01-22 10:45:04 +00:00 |
|
|
|
51a6cab753
|
Wire has_side_effect field in zml/ops.
|
2025-01-20 16:45:13 +00:00 |
|
|
|
99a2001e63
|
Rename PJRT BufferType to follow Zig and ZML naming conventions.
|
2025-01-16 13:00:47 +00:00 |
|
|
|
7324a49da3
|
Remove .print() calls from globalAttnMask() and localAttnMask() in ModernBERT example to resolve compilation sharding error.
|
2025-01-15 16:59:26 +00:00 |
|
|
|
09c43b8759
|
Add customCall operation to zml/ops.
|
2025-01-09 15:01:33 +00:00 |
|
|
|
9f1cc762cd
|
Fix map tests in zml/meta.
|
2025-01-06 17:49:50 +00:00 |
|
|
|
fbf1ecb8b7
|
Introduce Executable.getCompiledMemoryStats in PJRT.
|
2025-01-02 16:36:13 +00:00 |
|
|
|
4b1a3ff48a
|
Add union support to mapping helpers in zml/meta.zig.
|
2025-01-01 13:35:17 +00:00 |
|
|
|
c961d705f1
|
Set default values for operand_layouts and result_layouts in StableHLO dialect.
|
2024-12-26 09:29:45 +00:00 |
|
|
|
e6286b6097
|
Update Buffer.from to be blocking by default and add options for async loading and memory placement, adjusting aio, hostbuffer, pjrtx, and tensor implementations.
|
2024-12-25 17:14:44 +00:00 |
|
|
|
da1fd2d9dc
|
Add examples demonstrating Buffer.from options, non‑blocking loading, and memory copy behavior.
|
2024-12-20 09:30:35 +00:00 |
|
|
|
bb2b77d7de
|
Correctly set model.norm.eps in Llama examples.
|
2024-12-18 11:48:23 +00:00 |
|
|
|
6aa9aa5a7b
|
Add preliminary implementation for custom call support.
|
2024-12-10 09:36:37 +00:00 |
|
|
|
1d5b79111a
|
modernbert: set default epsilon value for embeddings layernorm.
|
2024-12-09 16:43:29 +00:00 |
|
|
|
a63d0a4aa3
|
Update example MODULE.bazel and lockfile to use the toolchains_llvm_bootstrapped configuration.
|
2024-12-04 11:30:44 +00:00 |
|
|
|
5464281c91
|
Update workspace configuration to use the toolchains_llvm_bootstrapped toolchain for Zig builds.
|
2024-12-03 13:50:58 +00:00 |
|
|
|
f5ab2c3a55
|
zml: eliminate compile-time fields from Bufferized, removing the need to pass undefined to exe.call for inlined arguments. Introduce BufferizedWithArgs in zml.testing for compileAndCall utility.
|
2024-11-28 12:24:39 +00:00 |
|
|
|
364a222dc1
|
Update example MODULE.bazel and lockfile to target XLA version 20250527.0‑cb67f2f.
|
2024-11-25 17:57:45 +00:00 |
|
|
|
95453c7242
|
Update XLA dependency to version 20250527.0‑cb67f2f and refresh related Bazel BUILD, MODULE, overlay and patch files.
|
2024-11-22 16:50:20 +00:00 |
|
|
|
fa13287931
|
workspace: upgrade to Zig 0.14.1 and handle empty tuple syntax &.{} being detected as *const @TypeOf(.{}).
|
2024-11-19 11:45:36 +00:00 |
|
|
|
d8a83830e8
|
runtimes: switch to Cloudflare Debian snapshots for more reliable dependency pinning.
|
2024-11-15 09:40:58 +00:00 |
|
|
|
ea3ce685a9
|
runtimes/neuron: bump runtime version and expose nrt.h header to Zig.
|
2024-11-14 13:37:47 +00:00 |
|
|
|
09da9c2982
|
Make zls.sh example explicitly set the ZLS runner target.
|
2024-11-06 16:22:44 +00:00 |
|
|
|
948c577205
|
Make ZLS runner target explicit in workspace BUILD files and update the zls.sh script accordingly.
|
2024-11-04 13:57:59 +00:00 |
|
|
|
47a4eda5f6
|
runtimes/cuda: expose cuda.h in the C namespace for CUDA runtimes, enabling custom calls to CUDA functions.
|
2024-11-01 13:27:24 +00:00 |
|
|
|
3849eb10b7
|
Add buffer and hostbuffer utilities with precise f32→bf16 conversion, type inference for loadBuffers, store expected input shapes, enhance meta.visit and JSON TaggedUnion support, and improve logging.
|
2024-10-28 11:21:46 +00:00 |
|
|
|
1540c6e85e
|
Update loader example to demonstrate new HostBuffer helpers and type‑inferred buffer loading.
|
2024-10-25 10:20:04 +00:00 |
|
|
|
048d7eb38e
|
third_party/sentencepiece: add missing protobuf_lite dependency and bump version.
|
2024-10-22 16:41:52 +00:00 |
|
|
|
4ef81b89ea
|
stdx.fmt: add slice formatting support, improving on previous prettyPrinter implementation by leveraging internal fmt mechanisms.
|
2024-10-18 15:05:08 +00:00 |
|
|
|
fe55c600d4
|
Add/refresh how‑to docs and example loader for deployment, Docker, HuggingFace token, and getting‑started tutorials.
|
2024-10-14 11:27:41 +00:00 |
|
