最新模型

新模型、開放權重、多模態、語音、影像與模型架構。

Transformers Community Reports SAM 3 Prompt Structure Difference; Text-Only Path May Omit Geometry CLS Token

A Transformers community report on October 14 says SAM 3 skips the geometry encoder for text-only prompts, making the input structure differ from Meta’s reference implementation. Participants reported independent reproduction and proposed a fix, but maintainers have not confirmed the expected behavior, and any impact on segmentation accuracy remains unmeasured.

2026-10-09

GitHub Repo

MCP Python SDK Community Reports Large-Response Bottleneck, with Repeated Buffer Copies Causing Quadratic Cost

Community reports from October 13–14 indicate that receiving large tool responses over stdio in the MCP Python SDK can add substantial latency because of repeated buffer copies. Contributors have shared a minimal reproduction and before-and-after test results, but no official fix has been released.

2026-10-15

GitHub Repo

Ollama Pre-release Ports MLX Custom Kernels to CUDA; Limited Tests Show Nemotron Prompt Throughput More Than Doubling

Ollama released v0.40.5-rc0 on October 14, adding CUDA ports of three groups of MLX custom kernels and reducing fallback to computation graph operations. The author measured more than a twofold increase in prompt throughput for two Nemotron models on an RTX 6000 Ada, but results have yet to be validated across hardware and full workloads.

2026-10-11

GitHub Repo

HelixWorld Releases HelixBench to Evaluate Whether Generated Soundscapes Follow Viewpoint Changes

Noiz AI and the Hong Kong University of Science and Technology’s HelixWorld project released HelixBench on October 12, with 1,015 fixed test cases and evaluation code. The benchmark separately checks audio quality, audio-video synchronization, and spatial sound consistency. The public package does not include the source videos, so take care to follow the scoring protocol when reproducing results.

2026-10-14

GitHub Repo

Transformers community reports lost tokenizer normalization, possible extra newline token in WeMM embeddings

A Transformers report on October 13 says a newer tokenizer loading path may ignore the model’s existing normalization settings, adding a trailing newline token to WeMM-Embedding-2B inputs. The report includes a cross-version minimal reproduction, but maintainers have not confirmed it and retrieval quality has not been measured.

2026-10-14

Liquid AI Releases LFM2.5-24B-A2B, Expanding Long-Context and Local Agent Tooling Capabilities

On October 13, Liquid AI unveiled LFM2.5-24B-A2B and base model weights, extending context to 131,072 tokens and switching to a fixed reasoning-before-answering format. The company published local decoding and agent benchmark results, but deployers should still validate end-to-end task latency, tool parsing, and post-quantization quality.

2026-10-14

GitHub Repo

Hermes Agent v0.22.0 Integrates Local Model Management and Defaults to Stable Updates

Hermes Agent v0.22.0 adds llama.cpp downloads, hardware adaptation, and model memory management. Source installs now track stable releases by default, and a package management process that verifies a new environment before switching aims to reduce update interruptions.

2026-10-12

GitHub Repo

Transformers Community Proposes RoPE Configuration Compatibility Fix; Legacy Overrides May Lose Model Base Parameters

An October 12 Transformers report says that applying a legacy `rope_scaling` configuration after initialization may clear existing RoPE base parameters, causing initialization to fail or a reload to use default values. The proposed fix includes ten regression tests, but has not been merged; maintainers have also questioned whether users should migrate to the newer configuration interface.

2026-10-12

GitHub Repo

Transformers Community Reports LLMDet Weight-Sharing Bug That May Shift Detection Boxes

A report posted on October 12 says MM Grounding DINO and LLMDet may ignore configuration during loading and bind detection heads from different decoder layers to the same weights. It includes reproduction code and coordinate comparisons, but maintainers have not confirmed the issue, issued an official fix, or provided a full accuracy evaluation.

2026-10-13

GitHub Repo

Transformers Community Reports Gemma Tensor Parallelism Bug; Mixing Tensor and DTensor May Interrupt Inference

Reports from the October 12–13 Transformers development builds indicate that Gemma 3 and 4 multimodal classes may fail to complete a forward pass under tensor parallelism because of inconsistent tensor types. The report includes a minimal reproduction, and its author points to a proposed fix, but the impact on stable releases and the completeness of the fix remain unconfirmed.

2026-10-09

GitHub Repo

Ollama Pre-release Switches to Native Decision Inference in llama.cpp; Older GGUF Models May Need to Be Re-downloaded

On October 12, Ollama merged an update to its decision-model inference path and included it in v0.40.4-rc1, delegating prompt assembly and scoring to llama.cpp. The update also changes scoring requirements and model metadata, so existing deployments should verify model-file compatibility.

2026-10-13

GitHub Repo

Ollama Community Reports Discrepancy in Prompt Throughput Calculation; Cache Hits May Inflate Performance Figures

A report posted to the Ollama community on October 11 says the OpenAI-compatible endpoint may divide the total number of prompt tokens, including cached tokens, by the processing time for uncached tokens, inflating prompt throughput. The report includes a streaming response and reproduction steps, but the fix status and cross-version impact remain unconfirmed.

2026-09-23