←Search results

Search “GitHub”

By relevance · Total 1629 results Clear search

Tuesday

  1. Claude Code：GitHub Releases

    Claude Code v2.1.304 released

    Claude Code v2.1.304 adds a guided `/auto-mode-setup` setup that can read the project and recent sessions to let auto mode understand the environment, and now supports Bedrock, Vertex, Foundry, the Claude apps gateway, and sessions with telemetry disabled. This version also adds `/claude-api managed-agents-secure`, which checks Managed Agents configuration against Anthropic's public security guidelines without making any changes. In addition, it fixes several issues, including Linux sandbox command startup, the `rm -r` mounted-drive safety prompt, and plugins continuing to run beyond `--max-turns`.

    Claude Code v2.1.304 adds a guided /auto-mode-setup setup that can read the project and recent sessions to let auto mode understand the environment, and now supports Bedrock, Vertex, Foundry, the Claude apps gateway, and sessions with telemetry disabled. This version also adds /claude-api managed-agents-secure , which checks Managed Agents configuration against Anthropic's public security guidelines without making any changes. In addition, it fixes several issues, including Linux sandbox command

    Matched fieldsBody

    #engineering#Product updates#English text is being prepared.#Anthropic
  2. NVIDIA：Newsroom

    NVIDIA Completes 104-Qubit Fault-Tolerant Quantum Computing Simulation at Jülich Supercomputing Center

    NVIDIA has completed a 104-qubit fault-tolerant quantum computing simulation on the JUPITER supercomputer at the Jülich Supercomputing Center in Germany, calling it the largest complete simulation of a fault-tolerant quantum processor to date. The simulation validated the magic state cultivation method, requiring 90% fewer physical qubits than previous methods, and ran under real noise conditions. The research team first developed the method on the GB200 NVL72 system at NVAQC, then scaled it to 8,192 GPUs on JUPITER, using cuQuantum and CUDA-Q to complete the computation.

    NVIDIA has completed a 104-qubit fault-tolerant quantum computing simulation on the JUPITER supercomputer at the Jülich Supercomputing Center in Germany, calling it the largest complete simulation of a fault-tolerant quantum processor to date. The simulation validated the magic state cultivation method, requiring 90% fewer physical qubits than previous methods, and ran under real noise conditions. The research team first developed the method on the GB200 NVL72 system at NVAQC, then scaled it to

    Matched fieldsBody

    #ai-news#Industry news#English text is being prepared.#English text is being prepared.
  3. AWS Machine Learning

    How vLLM's bidirectional KV transfer improves TTFT for multi-turn agent workloads

    vLLM adds bidirectional KV transfer, allowing decode nodes to send already-computed KV caches back to prefill nodes in subsequent turns, avoiding recomputation of conversation history. On a 1P1D deployment on Amazon EC2 P5en, this mechanism improves TTFT by up to 1.6x for Qwen3-32B and up to 3.3x for zai-org/GLM-5-FP8. This capability was initially validated on AWS Trainium clusters and contributed to vLLM; as an accelerator-agnostic feature, it requires coordination with a KV-cache-aware router for cross-turn reuse.

    Flow diagram contrasting the standard prefill-to-decode KV path (blue) with the bi-directional additions numbered one through six (red)

    vLLM adds bidirectional KV transfer, allowing decode nodes to send already-computed KV caches back to prefill nodes in subsequent turns, avoiding recomputation of conversation history. On a 1P1D deployment on Amazon EC2 P5en, this mechanism improves TTFT by up to 1.6x for Qwen3-32B and up to 3.3x for zai-org/GLM-5-FP8. This capability was initially validated on AWS Trainium clusters and contributed to vLLM; as an accelerator-agnostic feature, it requires coordination with a KV-cache-aware router

    Matched fieldsBody

    #lab#Tutorials / practice#English text is being prepared.#Reasoning
  7. Unite.AI

    Town Completes $108 Million Series B Funding, Valued at $1 Billion

    Town announced on October 19, 2026 that it had completed a $108 million Series B funding round, co-led by Forerunner Ventures and Menlo Ventures, at a valuation of $1 billion, with participation from existing investors including a16z and First Round Capital. Town's AI work assistant Townie can now collaborate directly with one another, asking each other questions, connecting context across teams, and handing off work, while still sharing information only within the scope authorized by each respective user. The company says that since July 2026, its paid customers have grown 4x and paid teams 9x, and it supports more than 60 integrations.

    Town announced on October 19, 2026 that it had completed a $108 million Series B funding round, co-led by Forerunner Ventures and Menlo Ventures, at a valuation of $1 billion, with participation from existing investors including a16z and First Round Capital. Town's AI work assistant Townie can now collaborate directly with one another, asking each other questions, connecting context across teams, and handing off work, while still sharing information only within the scope authorized by each respe

    Matched fieldsBody

    #hot-signal#Industry news#Agents

Monday

Sunday

Saturday

  3. cnBeta

    Claude web and desktop now offer a Chinese interface, but mainland China is still not on the list of supported regions

    Claude web and desktop have added a language selector, and the interface now supports Chinese (Simplified) and Chinese (Traditional), among more than thirty languages; the mobile app has not yet followed suit. In the billing country drop-down menu on the checkout page, China appears, and both the $20 Pro and $200 Max plans are selectable, but the official list of supported regions still does not include mainland China, Hong Kong, or Macao. Anthropic has previously imposed account bans and identity verification restrictions on access from unsupported regions; this Chinese interface is mainly aimed at overseas Chinese users.

    Claude web and desktop have added a language selector, and the interface now supports Chinese (Simplified) and Chinese (Traditional), among more than thirty languages; the mobile app has not yet followed suit. In the billing country drop-down menu on the checkout page, China appears, and both the $20 Pro and $200 Max plans are selectable, but the official list of supported regions still does not include mainland China, Hong Kong, or Macao. Anthropic has previously imposed account bans and identi

    Matched fieldsBody

    #hot-signal#Product updates#Anthropic
  4. Claude Code：GitHub Releases

    Claude Code v2.1.302 Released

    Claude Code has released v2.1.302, adding the CLAUDE_CODE_AUTO_MODE_MODEL environment variable to select the model used by the client-side auto mode classifier, and adding an Idle compaction toggle in /config. This version also fixes issues such as "Prompt is too long" being reported when stopping a turn while compacting a conversation, request failures after switching to Vertex or Bedrock mid-session, and the Read tool loading image sources larger than 128 MB entirely into memory, and improves multi-plugin startup speed and auto mode server-side classifier handling.

    Claude Code has released v2.1.302, adding the CLAUDE CODE AUTO MODE MODEL environment variable to select the model used by the client-side auto mode classifier, and adding an Idle compaction toggle in /config. This version also fixes issues such as "Prompt is too long" being reported when stopping a turn while compacting a conversation, request failures after switching to Vertex or Bedrock mid-session, and the Read tool loading image sources larger than 128 MB entirely into memory, and improves

    Matched fieldsBody

    #engineering#Product updates#Agents#English text is being prepared.