🚀 New Release Alert!
📦 llama.cpp
🏷 Category: AI
🔖 Version:
📅 Released: 2026-05-30 14:25 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
TP: fix granularity for Qwen 3.5/3.6 + 3 GPUs (#23843)
TP: fix granularity for Qwen 3.5/3.6 + 3 GPUs
fix afmoe TP
</details>
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
📥 Download Release
📦 llama.cpp
🏷 Category: AI
🔖 Version:
b9434📅 Released: 2026-05-30 14:25 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
TP: fix granularity for Qwen 3.5/3.6 + 3 GPUs (#23843)
TP: fix granularity for Qwen 3.5/3.6 + 3 GPUs
fix afmoe TP
</details>
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
📥 Download Release
🚀 New Release Alert!
📦 llama.cpp
🏷 Category: AI
🔖 Version:
📅 Released: 2026-05-30 17:43 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
opencl: support bf16 by converting to f16 (#23839)
</details>
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
📥 Download Release
📦 llama.cpp
🏷 Category: AI
🔖 Version:
b9436📅 Released: 2026-05-30 17:43 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
opencl: support bf16 by converting to f16 (#23839)
</details>
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
📥 Download Release
🚀 New Release Alert!
📦 llama.cpp
🏷 Category: AI
🔖 Version:
📅 Released: 2026-05-30 20:56 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
Support
Support `-fa auto` in llama-bench
Make the default value of `-ngl` -1, similar to other tools.
Update README with latest usage and examples
Address review comments
</details>
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS ...
🔗 View on GitHub
📥 Download Release
📦 llama.cpp
🏷 Category: AI
🔖 Version:
b9437📅 Released: 2026-05-30 20:56 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
Support
-fa auto in llama-bench (#23714)Support `-fa auto` in llama-bench
Make the default value of `-ngl` -1, similar to other tools.
Update README with latest usage and examples
Address review comments
</details>
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS ...
🔗 View on GitHub
📥 Download Release
🚀 New Release Alert!
📦 MITM-DomainFronting
🏷 Category: Community Suggested
🔖 Version:
📅 Released: 2026-05-30 21:21 UTC
📊 Assets: 0 files
📝 What's New:
Add DOH; Add meta (facebook, instagram, whatsapp, ...); Unrestricted youtube
🔗 View on GitHub
📥 Download Release
📦 MITM-DomainFronting
🏷 Category: Community Suggested
🔖 Version:
MITM-DomainFronting v22📅 Released: 2026-05-30 21:21 UTC
📊 Assets: 0 files
📝 What's New:
Add DOH; Add meta (facebook, instagram, whatsapp, ...); Unrestricted youtube
🔗 View on GitHub
📥 Download Release
❤1👎1😍1
🚀 New Release Alert!
📦 llama.cpp
🏷 Category: AI
🔖 Version:
📅 Released: 2026-05-31 06:57 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
llama: only use one iGPU device by default (#23897)
</details>
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
📥 Download Release
📦 llama.cpp
🏷 Category: AI
🔖 Version:
b9439📅 Released: 2026-05-31 06:57 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
llama: only use one iGPU device by default (#23897)
</details>
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
📥 Download Release
🚀 New Release Alert!
📦 llama.cpp
🏷 Category: AI
🔖 Version:
📅 Released: 2026-05-31 09:49 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
ui: fix ETag truncation with MSVC compiler (#23917)
</details>
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
📥 Download Release
📦 llama.cpp
🏷 Category: AI
🔖 Version:
b9441📅 Released: 2026-05-31 09:49 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
ui: fix ETag truncation with MSVC compiler (#23917)
</details>
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
📥 Download Release
🚀 New Release Alert!
📦 shadcn/ui
🏷 Category: UI Library
🔖 Version:
📅 Released: 2026-05-31 12:19 UTC
📊 Assets: 0 files
📝 What's New:
### Minor Changes
- #10834 `8e2d2d1439f54260aa0c51747261c220334ec641` Thanks @shadcn! - add npx shadcn eject
🔗 View on GitHub
📥 Download Release
📦 shadcn/ui
🏷 Category: UI Library
🔖 Version:
shadcn@4.9.0📅 Released: 2026-05-31 12:19 UTC
📊 Assets: 0 files
📝 What's New:
### Minor Changes
- #10834 `8e2d2d1439f54260aa0c51747261c220334ec641` Thanks @shadcn! - add npx shadcn eject
🔗 View on GitHub
📥 Download Release
🚀 New Release Alert!
📦 claude-code
🏷 Category: Community Suggested
🔖 Version:
📅 Released: 2026-05-31 19:42 UTC
📊 Assets: 10 files
📝 What's New:
## What's changed
- Internal infrastructure improvements (no user-facing changes)
🔗 View on GitHub
📥 Download Release
📦 claude-code
🏷 Category: Community Suggested
🔖 Version:
v2.1.159📅 Released: 2026-05-31 19:42 UTC
📊 Assets: 10 files
📝 What's New:
## What's changed
- Internal infrastructure improvements (no user-facing changes)
🔗 View on GitHub
📥 Download Release
🚀 New Release Alert!
📦 llama.cpp
🏷 Category: AI
🔖 Version:
📅 Released: 2026-05-31 21:51 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
server : handle If-None-Match weak ETags (#23916)
</details>
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
📥 Download Release
📦 llama.cpp
🏷 Category: AI
🔖 Version:
b9444📅 Released: 2026-05-31 21:51 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
server : handle If-None-Match weak ETags (#23916)
</details>
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
📥 Download Release
🚀 New Release Alert!
📦 v2rayNG
🏷 Category: Community Suggested
🔖 Version:
📅 Released: 2026-05-27 12:13 UTC
📊 Assets: 10 files
📝 What's New:
### 本次更新
- 将 target SDK 版本提升至 37 (Android 17)
- 路由中的出站支持策略组
- 添加分享日志 https://github.com/2dust/v2rayNG/pull/5682
🔗 View on GitHub
📥 Download Release
📦 v2rayNG
🏷 Category: Community Suggested
🔖 Version:
📅 Released: 2026-05-27 12:13 UTC
📊 Assets: 10 files
📝 What's New:
### 本次更新
- 将 target SDK 版本提升至 37 (Android 17)
- 路由中的出站支持策略组
- 添加分享日志 https://github.com/2dust/v2rayNG/pull/5682
🔗 View on GitHub
📥 Download Release
❤2
🚀 New Release Alert!
📦 MITM-DomainFronting
🏷 Category: Community Suggested
🔖 Version:
📅 Released: 2026-06-01 02:10 UTC
📊 Assets: 0 files
📝 What's New:
prevent crash after DNS flood
🔗 View on GitHub
📥 Download Release
📦 MITM-DomainFronting
🏷 Category: Community Suggested
🔖 Version:
MITM-DomainFronting v23📅 Released: 2026-06-01 02:10 UTC
📊 Assets: 0 files
📝 What's New:
prevent crash after DNS flood
🔗 View on GitHub
📥 Download Release
❤1
🚀 New Release Alert!
📦 Vite
🏷 Category: Build Tool
🔖 Version:
📅 Released: 2026-06-01 04:14 UTC
📊 Assets: 0 files
📝 What's New:
Please refer to CHANGELOG.md for details.
🔗 View on GitHub
📥 Download Release
📦 Vite
🏷 Category: Build Tool
🔖 Version:
v8.0.15📅 Released: 2026-06-01 04:14 UTC
📊 Assets: 0 files
📝 What's New:
Please refer to CHANGELOG.md for details.
🔗 View on GitHub
📥 Download Release
🚀 New Release Alert!
📦 Vite
🏷 Category: Build Tool
🔖 Version:
📅 Released: 2026-06-01 10:16 UTC
📊 Assets: 0 files
📝 What's New:
Please refer to CHANGELOG.md for details.
🔗 View on GitHub
📥 Download Release
📦 Vite
🏷 Category: Build Tool
🔖 Version:
v7.3.5📅 Released: 2026-06-01 10:16 UTC
📊 Assets: 0 files
📝 What's New:
Please refer to CHANGELOG.md for details.
🔗 View on GitHub
📥 Download Release
🚀 New Release Alert!
📦 shadcn/ui
🏷 Category: UI Library
🔖 Version:
📅 Released: 2026-06-01 10:59 UTC
📊 Assets: 0 files
📝 What's New:
### Minor Changes
- #10842 `7c63c467361dee9e20631b2999040912439b35d4` Thanks @shadcn! - add support for GitHub registries. See the docs.
🔗 View on GitHub
📥 Download Release
📦 shadcn/ui
🏷 Category: UI Library
🔖 Version:
shadcn@4.10.0📅 Released: 2026-06-01 10:59 UTC
📊 Assets: 0 files
📝 What's New:
### Minor Changes
- #10842 `7c63c467361dee9e20631b2999040912439b35d4` Thanks @shadcn! - add support for GitHub registries. See the docs.
🔗 View on GitHub
📥 Download Release
🚀 New Release Alert!
📦 Vite
🏷 Category: Build Tool
🔖 Version:
📅 Released: 2026-06-01 09:50 UTC
📊 Assets: 0 files
📝 What's New:
Please refer to CHANGELOG.md for details.
🔗 View on GitHub
📥 Download Release
📦 Vite
🏷 Category: Build Tool
🔖 Version:
v8.0.16📅 Released: 2026-06-01 09:50 UTC
📊 Assets: 0 files
📝 What's New:
Please refer to CHANGELOG.md for details.
🔗 View on GitHub
📥 Download Release
🚀 New Release Alert!
📦 llama.cpp
🏷 Category: AI
🔖 Version:
📅 Released: 2026-06-01 13:13 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
vulkan: Removed unused functions (#23175)
</details>
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
📥 Download Release
📦 llama.cpp
🏷 Category: AI
🔖 Version:
b9451📅 Released: 2026-06-01 13:13 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
vulkan: Removed unused functions (#23175)
</details>
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
📥 Download Release
🚀 New Release Alert!
📦 llama.cpp
🏷 Category: AI
🔖 Version:
📅 Released: 2026-06-01 14:56 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
model: Add EXAONE 4.5 implementations (#21733)
Add EXAONE 4.5 and Add GQA for MMproj
mtmd: EXAONE 4.5 vision markers and projector path
EXAONE 4.5 uses <vision> and </vision> for image boundaries; Qwen keeps
<|visionstart|> and <|visionend|>.
Route EXAONE 4.5 through the Qwen2.5-VL-style encode path (window attention
pattern, optional mmproj input norm). Update exaone4...
🔗 View on GitHub
📥 Download Release
📦 llama.cpp
🏷 Category: AI
🔖 Version:
b9453📅 Released: 2026-06-01 14:56 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
model: Add EXAONE 4.5 implementations (#21733)
Add EXAONE 4.5 and Add GQA for MMproj
mtmd: EXAONE 4.5 vision markers and projector path
EXAONE 4.5 uses <vision> and </vision> for image boundaries; Qwen keeps
<|visionstart|> and <|visionend|>.
Route EXAONE 4.5 through the Qwen2.5-VL-style encode path (window attention
pattern, optional mmproj input norm). Update exaone4...
🔗 View on GitHub
📥 Download Release
❤1
🚀 New Release Alert!
📦 React
🏷 Category: Frontend Framework
🔖 Version:
📅 Released: 2026-06-01 18:04 UTC
📊 Assets: 0 files
📝 What's New:
## React Server Components
- Fixed missing
(#36566 by @unstubbable)
🔗 View on GitHub
📥 Download Release
📦 React
🏷 Category: Frontend Framework
🔖 Version:
19.2.7 (June 1st, 2026)📅 Released: 2026-06-01 18:04 UTC
📊 Assets: 0 files
📝 What's New:
## React Server Components
- Fixed missing
FormData entries in Server Actions which regressed in 19.2.6(#36566 by @unstubbable)
🔗 View on GitHub
📥 Download Release
🚀 New Release Alert!
📦 llama.cpp
🏷 Category: AI
🔖 Version:
📅 Released: 2026-06-01 18:06 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
vulkan: reduce host memory lock contention (#23376)
vulkan: reduces lock contention
replace uniquelock with lockguard
</details>
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
📥 Download Release
📦 llama.cpp
🏷 Category: AI
🔖 Version:
b9457📅 Released: 2026-06-01 18:06 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
vulkan: reduce host memory lock contention (#23376)
vulkan: reduces lock contention
replace uniquelock with lockguard
</details>
macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
📥 Download Release
🚀 New Release Alert!
📦 llama.cpp
🏷 Category: AI
🔖 Version:
📅 Released: 2026-06-01 18:58 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
metal: template GLU kernels to support f16/f32 (#23882)
Drops the hardcoded f32 GLU kernels in favor of a single template. We now load/store in the native tensor type (half or float) to save memory bandwidth, but keep the actual ALU compute in float to avoid exploding math in geglu/swiglu. Also opened up the dispatch gate to allow f16 inputs.
</details>
macOS/iOS:
- macO...
🔗 [View on GitHub
📥 Download Release
📦 llama.cpp
🏷 Category: AI
🔖 Version:
b9459📅 Released: 2026-06-01 18:58 UTC
📊 Assets: 21 files
📝 What's New:
<details open>
metal: template GLU kernels to support f16/f32 (#23882)
Drops the hardcoded f32 GLU kernels in favor of a single template. We now load/store in the native tensor type (half or float) to save memory bandwidth, but keep the actual ALU compute in float to avoid exploding math in geglu/swiglu. Also opened up the dispatch gate to allow f16 inputs.
</details>
macOS/iOS:
- macO...
🔗 [View on GitHub
📥 Download Release
🚀 New Release Alert!
📦 Ollama
🏷 Category: AI
🔖 Version:
📅 Released: 2026-05-13 14:32 UTC
📊 Assets: 17 files
📝 What's New:
Ollama 0.30 is now available, with improved compatibility and performance using llama.cpp. This augments the MLX engine on Apple Silicon, bringing support to a wider range of hardware.
This release brings support for a wider range of models, including GGUF-based models from Hugging Face and your own fine-tuned models along with faster performance on N...
🔗 View on GitHub
📥 Download Release
📦 Ollama
🏷 Category: AI
🔖 Version:
v0.30.0📅 Released: 2026-05-13 14:32 UTC
📊 Assets: 17 files
📝 What's New:
Ollama 0.30 is now available, with improved compatibility and performance using llama.cpp. This augments the MLX engine on Apple Silicon, bringing support to a wider range of hardware.
This release brings support for a wider range of models, including GGUF-based models from Hugging Face and your own fine-tuned models along with faster performance on N...
🔗 View on GitHub
📥 Download Release