Daily edition · AI Tools
TILens turns technical updates into a focused daily brief: official releases, trusted reporting, and practitioner analysis, deduplicated and organized by topic.
which has efc not common_efc in the namespace of cutlass.operators.providers.cutedsl.evt. Pull Request resolved: #193940 Approved by: https://github.com/Skylion007
Changes since langchain-fireworks==1.5.2 release(fireworks): 1.6.0 (#39810) feat(fireworks): add document reranking (#39732) fix(fireworks): filter invalid tool calls from v1 content (#39805) feat(core): add standard…
Error when TORCH_TARGET_VERSION is newer than the libtorch being comp…
Corrects misspellings ("symbolicattion", "partfuseritioning", "merginginto", "dimensionalitities", "oldsyle", "semenatics", "archss", "Programmic"), missing word breaks ("offsetinto"), incorrect articles ("a int"/"an…
Summary Fixes #193938. When torch._inductor.config.align_random_eager=True, compiled torch.randn and torch.randn_like on CUDA were incorrectly lowered through ops.rand_eager, which produces uniform [0, 1) values. The FX…
Changes since langchain==1.3.15 release(langchain): 1.3.16 (#39806) feat(core): add standard model exception types (#39538) feat(langchain): support custom token_counter in ContextEditingMiddleware (#39754)…
Changes since langchain-anthropic==1.6.0 release(anthropic): 1.6.1 (#39804) fix(anthropic): filter invalid tool calls from v1 content (#39803)
Revert ideep for CPU to torch 2.13 version due to the performance reg…
Pull Request resolved: #194085 Approved by: https://github.com/Skylion007, https://github.com/fffrog
This PR fixes bugs in the Triton grouped MM kernel that only bite with really big tensors — some internal counters were the wrong bit-width and could overflow, causing crashes or bad output. Fixed those, added a guard…
In torch 2.13, different sorts of reductions either failed silently or loudly. We moved reductions from MPS Graph to metal kernels in 2.14 release window so now all of them fail silently which is undesirable. On 2.13:…
Remove condition preventing registration of some vmap decompositions …
[ghstack-poisoned]
Removed 'ndmitchell' from the list of approved reviewers. I used to be very active on the Pytorch type checking with Pyrefly, but now am working on other projects. The remaining approvers are all experts, so no loss of…
[fx] Memoize the result expression of symbolic binary arithmetic (#19…
[aoti] Add private libc++ build support, resolved from build_paths (#…
Dynamo previously had no handler for the DELETE_DEREF bytecode, which is emitted for del x when x is a cell variable (captured by a nested function) or a free variable. This models cell deletion the same way CPython…
Dynamo previously had no handler for the DELETE_DEREF bytecode, which is emitted for del x when x is a cell variable (captured by a nested function) or a free variable. This models cell deletion the same way CPython…
Removes # mypy: ignore-errors from torch/_numpy/_ndarray.py and enables strict pyrefly checking via a per-file sub-config, with no net-new pyrefly errors. _ndarray.py is the numpy-compatible ndarray wrapper over a…
docs: remove EOL Ubuntu 25.10 from get_start_xpu supported OS list (#…
Corrects article agreement ("an unbacked" / "a DTensorSpec"), subject-verb agreement ("we have recorded"), and a handful of typos ("staring" -> "starting", "fakefied" -> "fakified", "StorageWrite" -> "StorageWriter")…
Fix "a"/"an" article errors and typos in comments and docstrings (#19…
[Test] Improve test reuse in test/test_unary_ufuncs.py for out-of-tre…
Scalar clamp kernels converted bounds directly to the input dtype, causing out-of-range values to wrap or raise an exception, which is mathematically incorrect, as such bounds should become a no-ops. With this change,…
This PR is auto-generated nightly by this action. Update the pinned vllm hash. Pull Request resolved: #193866 Approved by: https://github.com/pytorchbot
This PR is auto-generated nightly by this action. Update the pinned vllm hash. Pull Request resolved: #193866 Approved by: https://github.com/pytorchbot
[ROCm][CI] Increase periodic MI300 distributed shards 3→5 to fix time…
[inductor] Guard mutation tests requiring Triton block pointers (#194…
This PR was authored with the assistance of an AI coding assistant. Co-Authored-By: Claude Opus 4.8 (1M context) noreply@anthropic.com Pull Request resolved: #191540 Approved by: https://github.com/hameerabbasi
[ghstack-poisoned]
update vision commit hash
update torchtitan commit hash
update vllm commit hash
update torchcomms commit hash
Update Metamates merge rule
Route MethodWrapperVariable.call_function to slotdef.__call__ (#192…
Implement mp_subscript / sq_concat / bool_impl for ConstantVariable (…
Problem #188429 pinned TheRock wheels with ==${ROCM_VERSION}, so 7.14 matches 7.14.0 but not a later patch such as 7.14.1. Changes Major.minor pins use prefix matching (==7.14.*). Fully specified preview pins stay exact…
[ghstack-poisoned]
