Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

ALL BRIEFS

RANKED · 8 THIS DAY

ONNX Patches Denial-of-Service Flaw in Sub-Byte Tensor Handling

ONNX disclosed CVE-2026-115922, a medium-severity denial-of-service vulnerability affecting all versions through 1.21.0, patched in version 1.22.0.

19d ago·Industry ProSINGLE SOURCE

ONNX Patches Out-of-Bounds Read in ConvTranspose Shape Inference

ONNX disclosed CVE-2026-115920, a medium-severity out-of-bounds read in ConvTranspose shape inference triggered when a weight tensor has fewer than three dimensions and no kernel_shape attribute is provided.

19d ago·Industry ProSINGLE SOURCE

PyTorch 2.15 Ships Rewritten NCCL Backend, Blackwell NVFP4 Decoding, Apple Silicon FP8

PyTorch 2.15, released October 28, makes a rewritten NCCL backend the default for every process group, adding a flight recorder that dumps on hangs and rollback paths via TORCH_DIST_USE_NCCL2=0 or nccl-legacy.

20d ago·Industry ProSINGLE SOURCE

Meta Andromeda Scores 1B+ Ads per Second, 100x Prior Throughput

Meta's next-generation Andromeda ads retrieval engine processes over one billion ads per second, a 100x throughput gain, and has lifted Facebook conversions 2.4% since 2025.

20d ago·Industry ProSINGLE SOURCE

Red Hat Details DRA for Distributed LLM Inference With RDMA and SR-IOV

Red Hat published a technical article on October 28 describing how Dynamic Resource Allocation (DRA) can improve performance of distributed large language model inference workloads using RDMA and SR-IOV.

20d ago·Industry ProSINGLE SOURCE