Search headlines, summaries and articles to connect the dots.
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.
The llama.cpp v1.21.70 release includes enhancements to the moe-cache system, introducing an LRFU/MQ-inspired hybrid cache with improved token handling, key computation, and decay calculations. Changes include adjusting the half-life parameter, increasing the number of classes to 8, refining score computation based on age, removing redundant branches, and improving documentation around unused slots and sorting. The release also features updated build binaries for multiple platforms including macOS, Linux, Windows, Android, and openEuler, with support for CUDA, Vulkan, ROCm, OpenVINO, SYCL, and other backends.
arXiv:2611.07211v1 Announce Type: new Abstract: Looped transformers scale inference-time reasoning by repeatedly reusing a shared core, increasing computation without increasing parameter count. Serving prefilling and decoding with a uniform loop budget couples their costs. We present LoopDuet, a phase-dependent depth and training-free serving approach that selects the two budgets jointly while preserving decoding depth at prefilling boundaries. Our vLLM implementation gathers tokens requiring further recurrence into compact batches, turning the selected allocation into executable savings with existing weights and attention kernels. At runtime, a queue-age controller adjusts prefilling depth to retain quality as demand changes. Experiments on the full HotpotQA dataset with one A100-80GB demonstrate two benefits of this flexibility. First, separate phase budgets improve the quality--throughput trade-off: Huginn delivers 19\% more throughput than the fastest tested uniform setting meeting the same accuracy criterion, while a higher-throughput operating point gains 6.04 EM points over uniform depth eight at 97\% of its throughput. Second, the same execution mechanism retains more quality under load: on two evaluated OLMo arrival traces, adaptive prefilling gains 0.92--1.35 EM points over the most accurate tested fixed-depth controls at the same 100\% attainment of a one-second time-to-first-token target. Together, these results establish LoopDuet as a practical way to turn flexible model computation into higher serving capacity and better quality under load.
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.
arXiv:2611.05451v1 Announce Type: new Abstract: While discrete tokenization in Unified Multimodal Models (UMMs) establishes strong semantic reasoning, it introduces a strict quantization bottleneck that degrades fine-grained visual details, often resulting in structurally accurate but artifact-heavy images. We introduce FlowShift, a parameter-efficient post-training framework that bypasses this bottleneck by converting pre-trained discrete UMMs into continuous rectified-flow generators. Instead of discarding the backbone's semantic priors, FlowShift replaces discrete visual interfaces with continuous latent projections and applies LoRA to the attention layers. To efficiently boost visual quality without semantic drift, we propose Dual-Objective Velocity Vector Distillation (DOVD), which aligns the model with a high-fidelity continuous teacher and ground-truth continuous trajectories. This approach drastically improves perceptual quality while preserving prompt adherence and reasoning. When applied to leading discrete UMMs, FlowShift significantly improves COCO-30K FID and aesthetic scores, while retaining over 99.5% of multimodal understanding capabilities. Ablations confirm DOVD drives generation quality. Ultimately, FlowShift achieves high-fidelity continuous generation without sacrificing pre-trained semantic grounding.
As artificial intelligence and accelerated computing continue to push the boundaries of what's possible, the latest NVIDIA CUDA release arrives to unlock...
The update resolves issues with -hf tag matching in longer quantization names, ensuring tags start at token boundaries. It also adds support for underscores as separators in quantization tags, improving compatibility with filenames like step3p5_flash_Q4_K_S-00001-of-00012.gguf.
arXiv:2611.04401v1 Announce Type: new Abstract: Context parallelism (CP) partitions long sequences across GPUs for LLM training and inference. For variable-length training and full prefill, attention-balanced placement can leave token loads uneven, while ring execution repeats overhead at each computation and communication step. In stage-serialized decode CP (DCP), long-running tasks delay dependent work and leave substantial GPU hardware idle. We propose LiquidCP, which unifies training and inference through a common model of Transfer, Compute, and Reduction tasks with tile-level dependencies, decoupling attention tasks from communication and kernel boundaries. For training and full prefill, MegaRing incorporates BuddyRing placement to balance attention and token loads, and coalesces ready KV regions during forward attention to amortize overhead. For decoding and mixed batches, MegaDCP selects history-KV splits by jointly modeling the completion of attention and its dependent reductions. A shared persistent GPU-resident engine executes both designs. Compared with the fastest baseline per configuration on eight H100 GPUs, MegaRing achieves geometric-mean core-attention speedups of $1.23\times$ forward and $1.18\times$ backward, and accelerates a Transformer layer by $1.08$--$1.16\times$. MegaDCP achieves geometric-mean core-attention speedups of $1.20\times$ for decode-only and $1.35\times$ for mixed batches. In vLLM serving with KV prefix cache, it achieves an average time-to-first-token speedup of $1.22\times$.
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.
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
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](
vLLM Semantic Router released d3-ultra, a 27B open-weight multimodal decision model. It reads text, images and video once, then returns probabilities for every answer, scoring 87.2 on the team’s SR-Text test. The post vLLM Semantic Router Releases d3-ultra: A 27B Open Multimodal Decision Model appeared first on MarkTechPost.
Hugging Face has officially released AnyLanguageModel 1.0, an open-source Swift framework fully compatible with the Apple Foundation Models API. It supports seamless switching between local models (MLX, llama.cpp, Core ML) and hosted models (OpenAI, Anthropic, Gemini, Hugging Face Inference Providers, etc.), and introduces new features such as image input, tool invocation, guided generation, and automatic adaptation of inference chunks.
