cuda

vLLM JSON output malformed after CUDA upgrade to 12.4

by
a close-up of a server room

Problem Description Symptoms and Impact After upgrading the Docker image to CUDA 12.4, vLLM v0.6.3 started emitting malformed JSON for function‑calling prompts. The downstream FastAPI gateway receives a truncated or syntactically invalid JSON payload, which triggers json.JSONDecodeError exceptions and causes request drops. Log snippet from a worker thread: INFO vllm.engine.output_parser – Received partial JSON: {“name”: “search”, “parameters”: … Read more

CUDA OOM during long sequence inference on NVIDIA GPU

by
the nvidia logo is displayed on a table

Problem Description On‑premise LLM inference nodes equipped with NVIDIA GPUs (e.g., A100 40 GiB, RTX 3090 24 GiB) crash when processing prompts that exceed the pre‑allocated key‑value (KV) cache size. The failure manifests as a CUDA out‑of‑memory (OOM) exception during the attention kernel launch. Typical log excerpts: [2026-08-10 14:32:07] ERROR – torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 2.00 … Read more

CUDA OOM error during model weight loading on GCP A100 instances

by
a close-up of a server room

Problem – CUDA OOM During Model Weight Loading on GCP A100 Instances When launching a multi‑GPU training job on a Google Cloud a2‑highgpu‑8g (8 × A100, 40 GiB each) or a2‑ultragpu‑1g (H100, 80 GiB) VM, the process aborts before the first optimizer step. The failure manifests as a CUDA out‑of‑memory (OOM) error during weight broadcast or activation checkpointing performed … Read more

CUDA OOM error during batched audio inference in PyTorch

by
a neon circle with a snake on it

Problem – Intermittent CUDA OOM and Tensor Shape Mismatches During Batched Audio Inference In a Kubernetes cluster that runs containerized PyTorch inference services, pods processing variable‑length audio streams occasionally crash with: CUDA out of memory. Tried to allocate 2.34 GiB (GPU 0; 8.00 GiB total capacity; 6.12 GiB already allocated; 1.23 GiB free; 6.12 GiB … Read more