Archive
Agent、MCP、coding agent、工作流自動化與評測。
GitHub Repo
A community report involving Transformers 5.12.0 says that after enabling the CPU memory-efficient loading option, other training processes may still allocate a full model, exhausting host memory. Official documentation says the option should prevent duplicate loading across processes, but the root cause and fix status await upstream confirmation.
GitHub Repo
A reproduction on a PyTorch development build shows that CUDA bicubic interpolation may return the input unchanged when a non-integer scale factor still produces the same output dimensions. A fix has been proposed but not merged; the impact on released versions remains unconfirmed.
GitHub Repo
A community reproduction on LangChain 1.4.0 suggests that passing an exception class directly to `retry_on` may cause models and tools to retry errors that do not match the intended filter. The official documentation calls for a tuple of exception classes or a predicate function; a fix and the full scope of impact remain unconfirmed.
GitHub Repo
After a Hermes Desktop update, the client may send RPC fields that an older Docker backend rejects, causing new conversations to fail. Official documentation confirms the two use different update mechanisms; the report highlights the need for protocol compatibility checks in agent deployments.
GitHub Repo
Dify’s MCP integration has been reported to mishandle resource_link content, potentially leaving tools that return only resource links with blank observations. A community patch to preserve links and metadata has been proposed but not merged; the impact on released versions remains unconfirmed.
GitHub Repo
A reproduction test with a large vocabulary suggests that the vLLM V1 CPU sampler may deviate from the model’s original probability distribution. The issue involves a fixed Gumbel random table; the impact on real models and an official fix remain to be confirmed.
GitHub Repo
A report says vLLM 0.30.0 does not apply PEFT’s per-layer rank and alpha settings, which could silently change adapter behavior. The community has provided a reproduction and a weight-conversion comparison; an official fix and the scope of impact remain unconfirmed.
最新模型
Clef and Clef-flash turn agent classification and routing into direct scoring of specified options, and release their weights under Apache 2.0. Official tests show latency advantages, but task accuracy and probability calibration still need to be validated against deployment data.
GitHub Repo
Non-admins with tool export permission could download the Python source code of tools shared with them as read-only. The issue was fixed in 0.11.4; operators should review group permissions and check whether credentials are embedded in code.
GitHub Repo
The new version moves language generation to the Agent API and changes model configuration, streaming events, and usage data formats. Existing PDF inputs and image and video results are no longer supported, while official sources still disagree about the Sonar deprecation timeline.
最新模型
Meituan’s new preview model retains a one-million-token context window and adds image understanding and coding-agent integrations. Official documentation lists inference controls, but the visual input format and performance on real tasks remain to be verified.
最新模型
The new version can output timestamped object trajectories, linking audiovisual perception to agent tool workflows. Available through the API and SDK, it requires attention to audio settings, output limits, and migration from older models.