🚀 New Release Alert!

📦 llama.cpp
🏷 Category: AI
🔖 Version: b9538
📅 Released: 2026-06-06 04:56 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

model : rename local nlayerall variable (#24209)

</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: b9542
📅 Released: 2026-06-06 10:47 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

completion : remove useless statics (#24226)

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

</details>

macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel ...

🔗 [View on GitHub
📥 Download Release

🚀 New Release Alert!

📦 Exclave
🏷 Category: Community Suggested
🔖 Version: 0.17.44
📅 Released: 2026-06-06 10:07 UTC
📊 Assets: 4 files

📝 What's New:
- Fix uTLS incorrectly applied to TrustTunnel HTTP/3 mode.

🔗 View on GitHub
📥 Download Release

🚀 New Release Alert!

📦 llama.cpp
🏷 Category: AI
🔖 Version: b9543
📅 Released: 2026-06-06 19:48 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

mtmd: support "frame merge" for qwen-vl-based models (#21858)

feat: add video support for Qwen3.5

various clean up

revise the design

fix llava-uhd case

nits

nits 2

---------

Co-authored-by: andrewmd5 <1297077+andrewmd5@users.noreply.github.com>

</details>

macOS/iOS:
- macOS Apple Silicon (arm64)
📥 Download Release

🚀 New Release Alert!

📦 llama.cpp
🏷 Category: AI
🔖 Version: b9544
📅 Released: 2026-06-06 21:20 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

common/chat : fix LFM2/LFM2.5 reasoning round-trip and <think> leak (#24234)

common/chat : fix LFM2 reasoning round-trip and stray <think> leak
Gate by reasoning format and whether the template supports <think>

</details>

macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS...

🔗 View on GitHub
📥 Download Release

🚀 New Release Alert!

📦 claude-code
🏷 Category: Community Suggested
🔖 Version: v2.1.168
📅 Released: 2026-06-06 23:41 UTC
📊 Assets: 10 files

📝 What's New:
## What's changed

- Bug fixes and reliability improvements


🔗 View on GitHub
📥 Download Release

🚀 New Release Alert!

📦 android
🏷 Category: Community Suggested
🔖 Version: 5.0.0
📅 Released: 2026-06-07 06:16 UTC
📊 Assets: 6 files

📝 What's New:
What's new:
- Improved tunnel reliability and leak protection with new deferred endpoint bootstrapping
- Improved tunnel status monitoring with real time handshake status monitoring
- Kernel mode and ping monitoring removed
- Full config and live tunnel view in quick format
- Automatic ipv4/ipv6 endpoint fallback and recovery
- Added support got DoT and custom endpoints for peer resolution DNS
...

🔗 View on GitHub
📥 Download Release

🚀 New Release Alert!

📦 llama.cpp
🏷 Category: AI
🔖 Version: b9547
📅 Released: 2026-06-07 09:38 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

arg: Skip mmproj download when user supplied mmproj (#24239)

</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: b9548
📅 Released: 2026-06-07 12:10 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

spec : fix vocab compatibility check (#24256)

</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: b9549
📅 Released: 2026-06-07 13:38 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

llama : add Gemma4 MTP (#23398)

</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: b9550
📅 Released: 2026-06-07 15:55 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

kv-cache: follow the source cache size when sharing cells (#24267)

A fitted target context can end up smaller than the draft default, the
oversized assistant views then overflow the shared K/V tensors and trip
the ggmlview4d size assert during graph reserve.

</details>

macOS/iOS:
- macOS Apple Silicon (arm64)
📥 Download Release

🚀 New Release Alert!

📦 Svelte
🏷 Category: Frontend Framework
🔖 Version: svelte@5.56.3
📅 Released: 2026-06-07 18:30 UTC
📊 Assets: 0 files

📝 What's New:
### Patch Changes

- fix: ignore errors that occur in destroyed effects (#18384)

- fix: type BigInts in $state.snapshot(...) return values (#18388)


🔗 View on GitHub
📥 Download Release

🚀 New Release Alert!

📦 llama.cpp
🏷 Category: AI
🔖 Version: b9551
📅 Released: 2026-06-07 19:27 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

kv-cache : avoid kv cells copies (#24277)

</details>

macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
📥 Download Release

🚀 New Release Alert!

📦 thefeed
🏷 Category: Community Suggested
🔖 Version: v0.24.0
📅 Released: 2026-06-07 19:59 UTC
📊 Assets: 23 files

📝 What's New:
feat(ui): SVG icon system + Apple-HIG visual polish


باگ صفحه سیاه

باگ درست نشون ندادن اسم کانفیگ

اضافه کردن کانفیگ های عمومی دفید به داخل برنامه


## Downloads

| Platform | Archi...

🔗 View on GitHub
📥 Download Release

🚀 New Release Alert!

📦 llama.cpp
🏷 Category: AI
🔖 Version: b9555
📅 Released: 2026-06-08 11:08 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

metal : fix im2col 1D case (audio models) (#24220)

</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: shadcn@4.11.0
📅 Released: 2026-06-08 13:49 UTC
📊 Assets: 0 files

📝 What's New:
### Minor Changes

- #10886 `05eb2b968bdc769ad78df9628dc2260e1dec903c` Thanks @shadcn! - improve search command

### Patch Changes

- #10851 `7dfd933102fdb881f8abd24fc1ef11a669682b94`
📥 Download Release

🚀 New Release Alert!

📦 llama.cpp
🏷 Category: AI
🔖 Version: b9556
📅 Released: 2026-06-08 13:48 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

HIP: add gfx1152 and gfx1153 to RDNA3.5 (#24129)

</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: b9559
📅 Released: 2026-06-08 15:24 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

cli: fix spinner not show during prompt processing (#24283)

</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: b9564
📅 Released: 2026-06-08 17:08 UTC
📊 Assets: 0 files

📝 What's New:
<details open>

ggml-webgpu Implement 2D workgroups for scale, binary, and unary ops (#24044)

Only run webgpu CI on my fork

Add webgpu only workflow

Implement 2d workgroups for more operations

fix

Fix type

Move back to globalinvocationid

</details>

macOS/iOS:
- macOS Apple Silicon (arm64)
📥 Download Release

🚀 New Release Alert!

📦 llama.cpp
🏷 Category: AI
🔖 Version: b9566
📅 Released: 2026-06-08 18:07 UTC
📊 Assets: 20 files

📝 What's New:
<details open>

graph: guard iswa kqmask on its own buffer (#24294)

A SWA-only draft head (e.g. StepFun MTP) leaves the base sub-cache
empty, so its kqmask buffer stays null and asserts at load. Guard
each mask on its own buffer in setinput and canreuse, base and swa.

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

</details>

macOS/iOS:
- macOS Apple Silicon (arm64)
📥 Download Release

🚀 New Release Alert!

📦 llama.cpp
🏷 Category: AI
🔖 Version: b9567
📅 Released: 2026-06-08 19:02 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

server : do not parse when flushing http headers (#24281)

</details>

macOS/iOS:
- macOS Apple Silicon (arm64)
- macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
- macOS Intel (x64)
📥 Download Release