Skip to content
AI NEWS.ccAI正在发生 未来正在更新
Bookmarks
THE JOURNAL
AI NEWS JOURNAL
AI, IN PERSPECTIVE

Search AI news

Search headlines, summaries and articles to connect the dots.

Newest first

llama.cpp releases

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.

llama.cpp releases

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.

llama.cpp releases

b12179

The update introduces support for 3D convolution (conv_3d) on Hexagon hardware by generalizing the existing conv_2d implementation. It leverages the HMX tiled path, folds kernel dimensions into a virtual row, and uses a shared solver with an is3d flag. The host computes unfold divisors to avoid device-side division, prevents DMA queue overflow, and improves tile size selection based on VTCM usage. Additional changes include handling arbitrary positive strides, preserving load/shuffle paths for small strides, and fixing compiler warnings.

llama.cpp releases

b12180

The release adds the Kimi-K3.1-Pro text model to llama.cpp, replacing full-attention MLA layers in K3 with DSA (Dynamic Sparse Attention) layers featuring a lightning indexer. The indexer uses an additive mask over the cache and reuses sparse flash attention paths, while preserving existing KDA layers and MoE components. The model's architecture includes four indexer tensors per DSA layer, hybrid memory for caching, and maintains quantization integrity by excluding indexer parameters from quant overrides. Verified against HF checkpoint with identical PPL beyond context length, and supports multiple platforms including macOS, Linux, Windows, Android, and iOS.

llama.cpp releases

b12136

The update addresses an issue in llama.cpp where the number of GPU layers was incorrectly calculated by not accounting for skipped NextN layers, leading to improper layer distribution between CPU and GPU. The fix ensures that skipped NextN layers are included in the n_gpu_layers count and properly assigned during model loading, resolving a bug where layer 0 remained on the CPU despite offloading all other layers.

vLLM · 官方技术博客

Migrating vLLM to the LibTorch Stable ABI

How vLLM migrated its CUDA build and compiled dependencies to the LibTorch Stable ABI, enabling compatible PyTorch upgrades without rebuilding vLLM.

llama.cpp releases

b12128

The fix addresses intermittent CI failures in TOPK_MOE tests caused by near ties in logits, particularly with uniform random inputs and narrow-range gating functions like sqrt_softplus. The solution involves redrawing logits until group selection and top-k decisions have a relative margin of 1e-4 in double precision, and constructing logits by inverting the gating function using a grid-based approach to ensure consistent expert selection across backends.

vLLM · 官方技术博客

vLLM Delivers Day-0 Support for Kimi K3.1 Pro

vLLM supports Kimi K3.1 Pro on day 0: sparse attention on a KDA hybrid, a packed KV cache with FP8 or NVFP4 latents and MXFP4 index keys, token-sharded prefill, decode context parallelism, and fused low-latency decode.

llama.cpp releases

b11946

server : add realtime conversation and transcription on /v1/realtime (#31269) * server : add realtime conversation and transcription on /v1/realtime Co-authored-by: Xuan Son Nguyen Assisted-by: Claude Opus 5.5 * examples : default the realtime client to the server port 9931 Assisted-by: Claude Opus 5.5 * server : sample realtime responses right after their own decode Slots respond in turns on one context: sampling at the start of the next step read the logits of whichever slot decoded last, so concurrent sessions mixed their outputs. Assisted-by: Claude Opus 5.5 * move more stuff to server-realtime, making it self-contained * examples : fix the type check of the realtime client Assisted-by: Claude Opus 5.5 * examples : use the model card prompts in the realtime client Assisted-by: Claude O

Timeline and related coverage

llama.cpp releases

b11933

vulkan: fix CI llvmpipe by allowing dim 3 broadcast in MUL_MAT (#31239) * vulkan: allow dim 3 broadcast in MUL_MAT supports_op rejected every MUL_MAT whose src0 and src1 differ in ne3, although mul_mm, mul_mmq and mul_mat_vec already broadcast src0 over dim 3 through broadcast3. Such a matmul then ran on the CPU with a copy of the weight, and the split layout changed with the number of streams in the ubatch. Keep the strict check for MUL_MAT_ID only, and route the broadcast cases away from mul_mat_vec_nc, the one path that requires equal ne3. * tests : harden MUL_MAT with permuted dim 3 broadcast cases Harden the MUL_MAT coverage with a weight broadcast over dim 3 against a permuted per-stream activation, the shape of an MLA output projection with a non unified KV cache, for a single token

Timeline and related coverage
llama.cpp releases

b11928

model: Add MiniCPM-OCR-Jev (#30980) * model : add MiniCPM-OCR-Jev support The model is a Qwen3.5-VL trunk with a value head read at the last token: it scores an OCR text against an image rendered from it, it does not generate. Add the openbmb-minicpm-ocr-jev decision type, served by POST /v1/systemone. The class scores are the pooled output of the sequence, read with last pooling, so the conversion turns score.weight into cls.output and sets embedding_length_out. The checkpoint has no LM head, so text generation is rejected instead of using the output weights duplicated from the token embeddings. The task is fixed, so its prompt is entirely in the systemone template, the same way h2o-lightning keeps its default there. The processor of the checkpoint allows up to 16384 merged tokens per ima

Timeline and related coverage
llama.cpp releases

b11927

metal : add GGML_OP_TOP_K_MASK (#31230) * metal : add GGML_OP_TOP_K_MASK Port the fused top-k mask from the CUDA backend: a grid-stride kernel fills the output with -inf, then one threadgroup per row copies the mask values of the kept cells over it. Function constants drop the score, blocks and extra paths that a given graph does not use. Assisted-by: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) * metal : clean up top-k mask kernel formatting Assisted-by: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11927/llama-b11927-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](

Timeline and related coverage
llama.cpp releases

b11907

models : replace ggml_tensor** out-params with output structs (#31142) The hyper-connection and DSA graph builders wrote their extra outputs (post / comb gates, carried top-k selections, inject gates) through ggml_tensor** out-params. Return them in a small struct next to the primary output instead. Assisted-by: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11907/llama-b11907-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b11907/llama-b11907-bin-macos-x64.tar.gz) - [

Timeline and related coverage

llama.cpp releases

b11895

metal : stop overflow from happening in large matrix output offsets (#30072) * Metal : stop overflow from happening in large matrix output offsets Assisted-by: Codex * metal : widen batch offsets and MUL_MAT_ID token indices Assisted-by: Codex --------- Co-authored-by: feni6 <270037094+feni6@users.noreply.github.com> **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11895/llama-b11895-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b11895/llama-b11895-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/dow

Timeline and related coverage

llama.cpp releases

b11877

vulkan: Add a larger tile size for conv3d (coopmat2 only) (#29920) * vulkan: Add a larger tile size for conv3d (coopmat2 only) This adds a larger tile size, in practice it is only for coopmat2 where we don't need shared memory to store the output (would use more than 64KB). Add some additional representative backend tests. At least, this is what codex came up with from looking at sd.cpp Wan VAE. * only apply large tile size for newer driver versions **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11877/llama-b11877-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama

Timeline and related coverage

Ollama

Reduce hallucinations with Bespoke-Minicheck

Bespoke-Minicheck is a new grounded factuality checking model developed by Bespoke Labs that is now available in Ollama. It can fact-check responses generated by other models to detect and reduce hallucinations.