All Articles · SURL AI News

Transformers Confirms Processor Parameter Override Issue; Mixing Template Parameters May Disable Input Truncation

A Transformers report on October 20 found that passing extra parameters unused by a template may override an explicitly configured input length limit. Project members have confirmed the issue, but parameter merge precedence is still under discussion, and no confirmed official fix has been released.

2026-10-20

GitHub Repo

Open WebUI Community Proposes Cancellation Write Patch for Persistent SQLite Locks After Interrupted Responses

An October 19 report on Open WebUI found that canceling a task while a response is being saved may prevent the database connection from being released, blocking subsequent writes. The community patch passed the reporter’s repeated-cancellation tests, but has not been merged, and no official fix version has been confirmed.

2026-10-05

GitHub Repo

Transformers Maintainers Confirm a Sampling Gap in Serve; Positive Temperature May Still Use Greedy Decoding

A Transformers report on October 19 found that some models may not enable random sampling when given a positive temperature through serve. Maintainers confirmed the issue and said they would rework the fix, but no confirmed release containing a fix was available.

2026-10-20

GitHub Repo

Transformers Reports Qwen3-MoE Loss Scaling Issue That May Amplify Router Auxiliary Weight in Multi-GPU Training

A Transformers report on October 19 says a specific Trainer setup may scale Qwen3-MoE’s router auxiliary loss with the number of data-parallel processes. A project member has responded with an analysis, but the available measurements use a fixed older version; no fix has been merged or released.

2026-10-20

GitHub Repo

LangChain Community Reports Counting Gap: Tool Limit May End Run Early and Allow Model Calls Past Cap

A LangChain community report on October 19 said that the ordering of two built-in middleware components may leave completed model calls uncounted, disabling cumulative conversation limits. Another contributor said they reproduced the issue and prepared a fix, but no maintainer confirmation or official fix release was available.

2026-09-27

GitHub Repo

Dify Community Reports Queued Nodes Starting After Workflow Stop, Potentially Allowing Later Tool Calls

A Dify community report on October 20 says queued nodes may still start after a workflow receives a stop signal, potentially adding model costs or triggering external actions. A proposed fix includes regression tests but has not been merged; the impact on official releases and the cloud service remains unconfirmed.

2026-10-20

MiniMax Releases M3.1 Flash, Targeting Low-Cost Agent Tasks and Million-Token Context

MiniMax launched M3.1 Flash on October 19, tuning sparse inference to improve speed and lower the cost of agent tasks. The model is available through an API, but its weights have yet to be released, and its official performance figures await independent verification.

2026-10-19

GitHub Repo

Firecrawl Community Reports DNS Rebinding Gap That Could Let Playwright Scraping Proxy Reach Internal Networks

A Firecrawl community report on October 20 said the Playwright scraping service resolves DNS separately for its checks and its actual connection, potentially allowing requests to bypass internal-address restrictions. A draft fix that reuses the checked DNS result was proposed the same day but has not been merged. Whether the hosted service is affected remains unconfirmed.

2026-10-20

Inception Releases Mercury 3, a Diffusion Language Model with One Million Tokens of Context

Inception launched Mercury 3 on October 19, expanding its context window to one million tokens and claiming output speeds of up to 1,068 tokens per second. Application developers have begun integrating it, but the company’s speed and quality comparisons still await independent evaluation.

2026-10-20

GitHub Repo

Dify Community Reports an Index Deletion Race That May Use Up RAG Retrieval Slots

A Dify community report on October 19 says deleting a document while it is being indexed may leave orphaned entries, causing retrieval to return fewer results than configured. A patch proposal includes tests but has not been merged and will not clean up existing orphaned data.

2026-10-10

GitHub Repo

Transformers 5.20.2 Fixes Lost Input Types in Generation and Includes BF16 Expert Gradient Patch

Hugging Face released Transformers 5.20.2 on October 19, fixing a bug that could discard input container types when moving inputs during generation and affect multimodal models. The release also formally includes a BF16 gradient patch for a specific expert-parallel configuration, providing a deployable version for an issue previously reported by the community.

2026-10-20

GitHub Repo

Transformers Community Reports Qwen4-Exp Cache Reset Gap That May Change Sparse Attention Results

A Transformers community report on October 19 says leftover position information may alter sparse attention selection when Qwen4-Exp reuses a reset cache. The report includes a reproduction and a local patch, but maintainers have not confirmed it, and evaluation with pretrained models remains incomplete.

2026-10-20