Coding Tools
llama.cpp b11001 fixes Spacemit transpose bug
llama.cpp Releaseshigh confidence
Why it matters
- →Fixes silent data corruption on Spacemit RISC-V hardware caused by incorrect vector instruction usage.
- →Updates binary support to include CUDA 13 and ROCm 10.0 for newer GPU ecosystems.
- →Ensures accuracy in flash attention operations for int16 quantization on specific accelerators.
llama.cpp has released version b11001 to address a critical bug affecting Spacemit processors. A previous implementation incorrectly used an s32 transpose function for int16 data, leading to corrupted results in matrix operations. The fix aligns the code with the correct s16 routine already present elsewhere in the flash attention module. This release includes updated binaries supporting CUDA 13 and ROCm 10.0 alongside standard CPU builds.
Read originalMore from llama.cpp Releases
Coding Toolscoding
llama.cpp b11000 fixes critical RCE in server
This release patches a critical remote code execution vulnerability in the llama.cpp server that allowed unauthenticated attackers to hijack memory via dangling pointers. The flaw stemmed from caching compute graphs that referenced freed buffers, enabling heap corruption and arbitrary code execution through subsequent tensor commands. By discarding cached graphs when buffers are freed, the fix forces a safe fallback to full recomputation without changing the API. This is a vital security update for anyone running the llama.cpp server remotely, closing a direct path to system compromise.
llama.cpp Releases
Coding Toolscoding
llama.cpp b11002 adds CUDA 13 and ROCm 10 support
This release quietly closes the hardware gap for local inference by adding native builds for CUDA 13 and ROCm 10.0 alongside existing CUDA 12 binaries. Users with newer NVIDIA GPUs or AMD accelerators no longer need to compile from source to get hardware acceleration, while Apple Silicon support remains available but explicitly disabled in this specific binary set. The simultaneous availability of these distinct backend versions means the runtime is now truly agnostic to the underlying GPU architecture. It is a pragmatic update that removes friction for anyone trying to run models on modern, non-CUDA-12 hardware.
llama.cpp Releases
Models & Labsmodels
llama.cpp adds support for DFM Mimir 1B HRM architecture
llama.cpp now runs the DFM Mimir 1B model, a rare example of a hierarchical recurrent transformer that alternates between two distinct processing cycles. This isn't just another standard decoder; it requires handling aliased cache slots and looped graph builds, pushing the runtime's architectural flexibility further than usual. While the decode speed is roughly four times slower than a dense model of similar width due to these 128 block passes, local inference for this specific architecture was previously impossible on consumer hardware. This release effectively opens the door for experimenting with non-standard transformer topologies in open-source environments.
llama.cpp Releases
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.274 fixes MCP timeouts and session stability
This release targets the friction points that make local AI coding feel fragile. The most critical fix addresses MCP servers timing out after five minutes regardless of configuration, a major blocker for complex agent workflows. Session reliability also improves with self-healing corrupted transcripts and better handling of background agents during resumption. While not feature-heavy, these patches stabilize the environment for developers relying on long-running automated tasks.
Claude Code Releases
© GitHub ChangelogCoding Toolscoding
GitHub automates SSO for PATs and SSH keys
GitHub Enterprise Cloud finally addresses the friction of manual SSO authorization for classic tokens and SSH keys. Admins can now delegate bulk authorization to GitHub Apps via a new API, handling up to 50 organizations in one request without exposing secrets. This shift from manual per-org clicks to automated delegation reduces the temptation to use insecure long-lived tokens. It is a practical infrastructure improvement that streamlines credential rotation for large enterprises managing complex access controls.
GitHub Changelog
© GitHub ChangelogCoding Toolscoding
GitHub SCIM adds profileUrl attribute
GitHub finally aligns its SCIM implementation with RFC 7643 by adding the profileUrl attribute to user responses. This small but necessary change eliminates the need for identity providers to perform extra lookups or infer account links when provisioning access. The update is additive, meaning existing integrations remain unaffected while new ones can now rely on a standardized field. It’s a quiet fix that reduces friction for enterprise IT teams managing GitHub access at scale.
GitHub Changelog