03:09
Make a Robot Arm Feel Weightless with NVIDIA Holoscan 5
Picture guiding a robot arm by hand while its motors supply just enough torque to support its weight and keep the robot upright. This simple interaction, a...
Today's news
Safety & governance / 01Exploring the world's languages with Language ExplorerGoogle Research
01 / IN FOCUS
Exploring the world's languages with Language Explorer
Google ResearchProducts & applications / 02Cisco research: Trust, not technology, is now the speed limit on enterprise AISiliconANGLE AI
02 / IN FOCUS
Cisco research: Trust, not technology, is now the speed limit on enterprise AI
SiliconANGLE AICompute & infrastructure / 03b12229llama.cpp releases
03 / IN FOCUS
b12229
llama.cpp releasesAI NEWS × FOXAIFind your next step
Explore AI tools From the latest news to tools that work for you.
Discover AI tools
Swipe to explore →K
KiroCoding & development
Open DesignDesign & 3D
JAXModels & infrastructure
EvoMapAgents & automation
AI ShortWriting & content
MemoAIMusic & audio
AssemblyAIMusic & audio
ElicitKnowledge & research
闪剪Video & animation
Meta AI助手Assistants & search
KiroCoding & developmentKiro is an AI engineering tool for developers that organizes requirements into specifications, architectures, and tasks, generates code via agents, and supports the entire workflow—from planning to code review—through property-based testing, execution memory, and integration with development tools.
分类推荐榜首OOpen DesignDesign & 3DOpenDesign is an open-source design workspace that can connect to local programming agents, use built-in model keys, or leverage cloud-based models, enabling the creation and editing of prototypes, web pages, presentations, and graphics within a design system; local software is free, while model services incur fees.
分类推荐榜首JJAXModels & infrastructureJAX is a Python numerical computing library designed for accelerators, specifically tailored for high-performance array computations and large-scale machine learning. It efficiently executes the same code across multiple hardware backends, including CPUs, GPUs, and TPUs.
分类推荐榜首EEvoMapAgents & automationEvoMap is an infrastructure designed for the reuse of AI agent experiences. It organizes reusable strategies and repair assets with validation records via the GEP protocol, offering market- and quality-based ranking to help different agents discover, evaluate, and inherit existing capabilities.
分类推荐榜首AAI ShortWriting & contentAIS ALERT MANAGEMENT AND SHARED PLATFORM, QUICK COMMAND FOR MULTIPLE SCENARIOS
分类推荐榜首MMemoAIMusic & audioMemoAI is an AI-powered audio-to-text tool that supports localized processing, eliminating the need to upload data and ensuring privacy and security. It can efficiently transcribe YouTube videos, podcasts, and local audio/video files (such as MP4, MP3, AAC, M4A, etc.) into text, while offering core features like multilingual translation, speaker diarization, real-time subtitles, and floating notes—making it ideal for meeting minutes, interview transcription, content learning, and more.
分类推荐榜首AAssemblyAI is a speech AI platform for developers, offering pre-recorded, real-time, and short-form synchronous transcription APIs. It enables the building of voice-based applications by integrating capabilities such as speaker identification, emotion analysis, chapter and summary extraction, as well as speech agent functionality, dictation, and sensitive information processing.
待评分 · 分类列表推荐EElicitKnowledge & researchElicit provides semantic search, research report generation, literature screening, and data extraction for scientific research. It enables traceable answers within source materials and organizes evidence through a literature library, research agents, and ongoing tracking workflows, making it ideal for advancing from initial problem exploration to systematic reviews.
待评分 · 分类列表推荐闪FlashCut is an AI-powered creation platform for voice-over and short-video marketing. It can generate finished videos with voiceovers, subtitles, and visuals from text, offering digital human customization, photo-to-digital-human conversion, live-stream clipping, and intelligent editing. It also provides APIs and branded mini-program solutions for businesses.
待评分 · 分类列表推荐MMeta AI助手Assistants & searchMeta's free AI chat assistant
待评分 · 分类列表推荐AI, as it happens
1540 published storiesInference systems & deployment · 142 storiesClear filters ×
2026-11-10
Follow the timeline00:41
b12229
A fix was implemented to ensure the OpenAI-compatible chat completions endpoint correctly processes JSON schema when provided at the top level in response_format.schema, rather than requiring it to be nested within response_format.json_schema.schema. The update also improves error messages, documents the correct usage in the README, and adds test cases to verify behavior, resolving issue #10732.
2026-11-09
Follow the timeline20:00
b12220
The Metal kernel for ggml_tri has been updated to use a select operation instead of scaling by comparison, aligning its behavior with the CPU kernel. This change ensures that values outside the triangle are set to zero rather than becoming NaN when encountering ±inf. A new test, test_tri_special, validates this fix across all four triangle types, confirming it passes with the update but failed previously.
13:00
ReKV: Overlapping Quantized KV Transfer and Suffix Recomputation
arXiv:2611.08770v1 Announce Type: new Abstract: Prefill--decode disaggregation moves a prompt's key--value (KV) cache between workers before the first token can be generated. Reducing this handoff to either cache compression or recomputation misses a useful choice: which layers to transmit, at what precision, and which layers to execute again on the decode worker. ReKV transfers a quantized prefix KV cache and one BF16 boundary state, then reconstructs a contiguous suffix while the prefix is in flight. In a model-shaped synthetic benchmark on cross-node H100s, the Q8 configuration meeting separately evaluated quality criteria reduces 8K handoff latency by $2.36\times$, $2.84\times$, and $3.65\times$ over BF16 transfer for Qwen2.5-7B, Qwen2.5-3B, and Qwen3-8B. It is also faster than the best measured transfer-only or recompute-only action at those points. A separate real-weight BF16 recomputation experiment reduces prefill-to-token-return time by $1.16$--$1.63\times$. The preferred action changes with prompt length and link bandwidth.
2026-11-08
Follow the timeline23:47
b12208
The ggml library has been updated to make tied selections in the radix Top-K algorithm deterministic on CUDA and Metal backends by replacing atomic compaction loops with a deterministic scheme using simdgroup scans and coalesced memory accesses. This change ensures byte-identical outputs across runs, improves performance by 20-45% on M5 Ultra hardware, and enables deterministic testing for Metal and ROCm. Redundant CUDA kernel resets were removed, and Vulkan/Metal changes were reduced or skipped.
22:20
b12207
A new fast path for d_state=64 has been added to the SSM_SCAN kernel in ggml-cuda, improving generation throughput for Zamba2-7B-Instruct from 11 to 15.1 tok/s—approximately a 35% increase—by eliminating CPU fallbacks for this state size. The change was verified with real-world Zamba2 hyperparameters and maintains correctness, though a separate 28% of scan calls still fall back to CPU due to an undiagnosed issue.
16:11
b12202
The llama.cpp v1.220.2 release introduces enhanced BF16 precision support across multiple components, aligning with reference implementations by moving specific operations like GLM4 family projections, MiMoVL vision matmuls, and Qwen3-TTS speaker encoder conv1d to BF16 where appropriate. Backends such as CUDA, Hexagon, OpenCL, WebGPU, and Vulkan now uniformly handle GGML_PREC_BF16 similarly to F32, while CPU, SpaceMIT, and ET backends extend flash attention support to BF16 with F32 accumulation. Flash attention tests now include BF16 cases, and the KQ multiplication in Llama is updated to request BF16 precision. A TODO remains in clip.cpp for future work.
14:58
b12201
The llama.cpp project has released version b12201, offering pre-compiled binaries for multiple platforms including macOS, Linux, Windows, Android, and iOS. The release includes support for various backends such as CUDA, Vulkan, ROCm, OpenVINO, SYCL, and Snapdragon hardware. Notably, the MoE cache feature is disabled for the draft model in this release. Additional resources include setup guides for Snapdragon devices and separate downloads for CUDA and OpenVINO libraries.
14:39
b12200
Enhancements to OpenCL support in llama.cpp include adding new kernel functions for quantized matrix operations, improving small-n MoE GEMV performance across multiple quantization types, optimizing Adreno GPU kernel floor settings, renaming functions for clarity, and disabling bin FA for small verification batches.
12:43
b12199
The release addresses the issue of invalid UTF-8 characters in arguments passed to PEG tool calls, improving input handling and robustness.
10:05
b12198
The llama.cpp release b12198 includes a change to downgrade per-request proxy logs to trace level, along with numerous precompiled binaries for macOS, Linux, Windows, Android, and other platforms, supporting various backends like CUDA, Vulkan, ROCm, OpenVINO, and SYCL. Some builds are disabled or experimental, including openEuler and KleidiAI-enabled macOS versions.
09:46
b12197
The update introduces support for automatic loading of libhtp without relying on legacy environment variables, enhances path handling for non-ASCII directories and long paths, adds platform-wide support for FASTRPC_MANAGE_DSP_LIBRARY_PATH and GGML_HEXAGON_LIBHTP_DIR, maintains forward slashes in absolute paths on Android and Linux, ensures absolute path precedence with fallback mechanisms, and includes CDSP1,2,3 in the fallback chain for IQ10 compatibility.
09:29
b12196
The release includes updates for SYCL backend with exact rounding support in CPY operations for Q4_1, Q5_1, and Q8_0 quantization formats.
09:11
b12195
The llama.cpp release b12195 introduces a change to refuse device buffers that would exceed VRAM, improving memory management. It includes precompiled binaries for multiple platforms including macOS, Linux, Windows, Android, and openEuler, with support for various backends such as CUDA, ROCm, Vulkan, OpenVINO, SYCL, and others. Some builds are marked as disabled or experimental.
07:45
b12193
The llama.cpp release b12193 includes a change to move log-mel computation to the cgraph, removes stray files, updates mtmd_audio_track to include source, and adds tests. It provides precompiled binaries for macOS, Linux, Windows, Android, and openEuler across various architectures and backends including CUDA, Vulkan, ROCm, OpenVINO, SYCL, and Snapdragon-specific platforms.
05:28
b12192
The latest release of llama.cpp adds support for the MageVL-Cowork model and adjusts how rope frequencies are handled, now stored at the model level within clip_model instead of being copied into each clip_layer. The loader verifies that rope_freqs is a 32-bit floating-point array with dimensions matching d_head, ensuring compatibility with expected 4:6:6 splits in the computational graph.
05:11
b12191
The latest update to llama.cpp introduces enhanced MoE (Mixture of Experts) cache functionality, enabling computation of cache misses on the CPU with a configurable CPU share. A new tuning script, moe-cache-tune.py, automatically determines optimal cache size and CPU share settings based on system performance. The update also improves scheduling efficiency, removes redundant sync operations, and refactors code for better maintainability, while maintaining compatibility across multiple platforms including macOS, Linux, Windows, and Android.
2026-11-07
Follow the timeline01:09
b12177
A fix has been implemented to prevent crashes in the command-line interface when encountering invalid UTF-8 in prompts or files, with assistance from Claude. This update is part of the b12177 release of llama.cpp, which includes various binary distributions for macOS, Linux, Windows, Android, and other platforms.
00:39
b12176
The update qualifies calls to math functions like isnan and signbit with std:: to ensure compatibility with C++ standard library overloads, addressing issues on NetBSD 11.99.9/x86_64 with gcc 14.4.0. Additional C math function calls are standardized using std:: prefixes (e.g., std::fabs, std::copysign) instead of non-existent std::fabsf variants, improving accuracy by keeping computations in double precision. The change results in a minor behavioral difference with a relative error of at most 1.4e-7, well below test tolerances.
00:07
b12175
A fix was implemented to override the hardware_concurrency value in CI tests, addressing an issue where test-llama-context and test-backend-ops hung due to incorrect thread count estimation on 8-CPU runners. The solution sets default values of 8 for TEST_ARG_HARDWARE_CONCURRENCY and 4 for TEST_ARG_PARALLEL_WORKERS specifically for the cpu-x64-high-perf configuration.
Every update links back to its source.