关注 Kimi 模型、长上下文、编程与 Agent 动态。
Kimi K3 from Moonshot AI is now available on Amazon Bedrock, giving you a powerful new open-weight option for coding and knowledge work. It offers native vision, a 1-million-token context window, and explicit prompt caching to reduce latency and input costs.
Mozilla’s State of Open Source AI report puts Kimi K3 about four months behind closed frontier models at 30% of the price. <p>Shane has a background in computer engineering and has worked as a freelance consultant in multiple industries. He has a strong affect
# v0.29.0 ## Highlights This release features 594 commits from 277 contributors (91 new)! * **Model Runner V2 is now the default for all models** (#53183), completing the rollout that began with pooling models (#48290). MRV2 also gained CUDA graph memory profi
# Highlights *786 PRs from 214 contributors.* **New models in this release** (see the [cookbook](https://docs.sglang.io/cookbook) for all supported models): | Model | Type | PRs | Cookbook | |---|---|---|---| | Qwen3.8 (2.4T-A95B) | Autoregressive | [#35758](h
模型仓库动态。仓库创建：2026-06-13T06:42:57.000Z。最后修改：2026-09-02T02:22:41.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：image-text-to-text。
## What's Changed * fix(kosong): omit empty anthropic-beta header when no beta features declared by @7Sageer in https://github.com/MoonshotAI/kimi-cli/pull/2580 * chore(release): bump kosong to 0.56.0 by @jackfish212 in https://github.com/MoonshotAI/kimi-cli/p
# v0.28.0 ## Highlights This release features 584 commits from 270 contributors (76 new)! * **Kimi-K3 performance push**: a major optimization effort for Kimi-K3 across the stack — Decode Context Parallel (DCP) support (#50484), fused FlashKDA decode and prefi
# Highlights *582 PRs from 194 contributors.* **Kimi K3 day-0 support**: A 2.8T-parameter multimodal LatentMoE (896 experts, top-16, routed in a 3584-dim latent space) with a 1M-token context, 69 KDA linear-attention layers interleaved with 24 MLA layers, and
# vLLM v0.27.0 Release Notes ## Highlights This release features 561 commits from 242 contributors (64 new)! * **Kimi K3 support** with a full stack landing in one release: core model files and kernels (#50089, #50000), Python (#50093) and Rust (#50104) fronte
chore(release): bump kosong to 0.56.0 (#2581)
## Highlight **Agent** - Support structured output (#2150) - Support environment information injection (#2134) **Workspace** - Support OpenSandbox (#1953), Daytona (#1943), K8s (#1933), Bubblewrap (#2051) **Tool** - Support PowerShell for Windows (#2132) **RAG
## What's Changed * fix(kimi): use remaining context for completion budget by @RealKai42 in https://github.com/MoonshotAI/kimi-cli/pull/2494 * fix(kosong): preserve empty-string reasoning_content as ThinkPart by @bigeagle in https://github.com/MoonshotAI/kimi-
Co-authored-by: jackfish212 jackfish212@outlook.com
# vLLM v0.25.0 Release Notes ## Highlights This release features 558 commits from 232 contributors (64 new)! * **Model Runner V2 is now the default for all dense models** (#44443). Building on quantized-model support from the previous release, MRv2 is now the
# Release v5.13.0 ## New Model additions ### KimiK 2.5, 2.6, and 2.7 This release includes the architecture for Kimi 2.5 which is used by 2.5-2.7: Kimi K2.5 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon
# Highlights New Model Support: [GLM-5.2](https://docs.sglang.io/cookbook/autoregressive/GLM/GLM-5.2), [LiquidAI LFM2.5](https://docs.sglang.io/cookbook/autoregressive/LiquidAI/LFM2.5), [Kimi-K2.7-Code](https://docs.sglang.io/cookbook/autoregressive/Moonshotai
## What's Changed * fix(kosong): round-trip empty reasoning content by @RealKai42 in https://github.com/MoonshotAI/kimi-cli/pull/2446 * feat(soul): escalate repeated-tool-call reminders and force-stop on dead-end streak by @jackfish212 in https://github.com/Mo
Co-authored-by: jackfish212 jackfish212@outlook.com
模型仓库动态。仓库创建：2026-06-11T07:51:47.000Z。最后修改：2026-06-15T07:49:29.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：image-text-to-text。
## What's Changed * fix(tools): include trailing output in error briefs and render brief as plain text by @liruifengv in https://github.com/MoonshotAI/kimi-cli/pull/2389 * docs: rename project to Kimi CLI and link to Kimi Code CLI successor by @RealKai42 in ht
## What's Changed * docs: announce evolution to Kimi Code successor project by @RealKai42 in https://github.com/MoonshotAI/kimi-cli/pull/2377 * docs: fix router auto language redirect by @RealKai42 in https://github.com/MoonshotAI/kimi-cli/pull/2378 * feat(she
## What's Changed * fix(shell): Fix misleading "Quota exceeded" prefix shown on every 403 error by @liruifengv in https://github.com/MoonshotAI/kimi-cli/pull/2342 * feat(toolset): improve dedup with sparse reminders and canonical args by @jackfish212 in https:
模型仓库动态。仓库创建：2026-04-14T04:23:36.000Z。最后修改：2026-05-19T09:01:54.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：image-text-to-text。
## What's Changed * refactor(telemetry): track btw side question as tool_call event by @jackfish212 in https://github.com/MoonshotAI/kimi-cli/pull/2257 * chore(release): bump kimi-cli and kimi-code to 1.44.0 by @jackfish212 in https://github.com/MoonshotAI/kim
## What's Changed * feat(ui): improve shell spacing, link highlighting and notification duration by @jackfish212 in https://github.com/MoonshotAI/kimi-cli/pull/2230 * feat(telemetry): polish event schema with outcome enum, lifecycle tracking and error enrichme
## What's Changed * fix(soul): clear partial UI output when LLM step is retried by @7Sageer in https://github.com/MoonshotAI/kimi-cli/pull/2177 * fix(tests): unbreak main CI after #2177 by @7Sageer in https://github.com/MoonshotAI/kimi-cli/pull/2213 * fix(shel
## What's Changed * fix(clipboard): enable clipboard paste on headless Linux over SSH by @ZichenWen1 in https://github.com/MoonshotAI/kimi-cli/pull/2115 * fix(plugin): support installing from .zip URL by @tempurai in https://github.com/MoonshotAI/kimi-cli/pull
模型仓库动态。仓库创建：2026-01-01T06:06:03.000Z。最后修改：2026-04-30T03:56:40.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：image-text-to-text。
模型仓库动态。仓库创建：2025-07-11T00:55:12.000Z。最后修改：2026-04-23T02:08:36.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：text-generation。
模型仓库动态。仓库创建：2025-06-21T09:40:28.000Z。最后修改：2026-01-30T04:53:11.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：image-text-to-text。
