Problemsby Ibisllama.cpp runs out of memory
DevOps and infra2 posts from 2 people2d active+00 posts in the last 7 days, 1 the 7 days before (fading)Unverified
Posts per day
The posts behind it
2, newest firstWindows/Vulkan/gfx1151: repeated failed allocations poison device memory until reboot (driver-side leak; reproducible)### Name and Version llama.cpp **b11429** (v0.6.0-dev, commit `d81235049`), official release build `llama-b11429-bin-win-vulkan-x64.zip` (ggml-vulkan.dll). ### Operating systems Windows 11 Home, build 26200. AMD Software **26.8.1**, driver **32.0.31041.1004** (2026-08-17). ###...ggml-org/llama.cpp · groundbreakersonline1 repliesOpen ↗Vulkan: aborts with no diagnostic on the Qualcomm Adreno driver (works on Turnip, same binary, same args)...reported here.) ## What I think is actionable Not "please support this driver" - the lack of any diagnostic. A pipeline or shader-compilation failure inside the backend currently produces a process that dies silently, which on Android is indistinguishable from an OOM kill and...ggml-org/llama.cpp · ArborPopuli6 repliesOpen ↗
Companies and products named
About this problem
Evidence
2 posts from 2 people in 1 place, about 1 a week over 9 days. Mostly on ggml-org/llama.cpp. Tools named alongside: Qualcomm, LM Studio, ASUS.
Frustration Frustration 0 of 3· Seen on GitHub issues
How it was grouped
Posts that state a pain and match the "oom" rule about llama.cpp. First post Oct 1, 2026, latest Oct 9, 2026. Unverified: fewer than 3 posts, or one person or place only. Method
The same problem elsewhere
Gemini runs out of memoryJobs and services run out of memoryGitHub runs out of memoryNVIDIA runs out of memoryDuckDB runs out of memoryApache Iceberg runs out of memoryPolars runs out of memoryvLLM runs out of memoryOllama runs out of memoryApache Airflow runs out of memoryMistral runs out of memory
Other llama.cpp problems
Running llama.cpp locally hits memory and speed limitsTrouble with llama.cpp miscllama.cpp users keep filing bugsllama.cpp upgrades break working setupsFine-tuning llama.cpp is costly and unpredictablellama.cpp runs out of context on real workTrouble with llama.cpp buildsllama.cpp lock-in makes switching costlyTrouble with llama.cpp flashTrouble with llama.cpp vulkan
History
steady to fading
llama.cpp runs out of memory (2 posts)