🚀 New Release Alert!

📦 llama.cpp
🏷 Category: AI
🔖 Version: b9480
📅 Released: 2026-06-02 16:23 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

StepFun 3.5 MTP (#23274)

StepFun 3.5 MTP

Simplify to single layer

Rollback core changes

fix flake8 errors

Remove scripts

modify to convention

Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

dos2unix

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

</details>

macOS/iOS:
- m...

🔗 [View on GitHub
📥 Download Release

🚀 New Release Alert!

📦 thefeed
🏷 Category: Community Suggested
🔖 Version: v0.22.0
📅 Released: 2026-06-02 20:06 UTC
📊 Assets: 23 files

📝 What's New:
## Downloads

| Platform | Architecture | Download |
|----------|-------------|----------|
| Linux | amd64 | server-سرور / client-کلاینت |
| Linux | arm64 | server-سرور
📥 Download Release

🚀 New Release Alert!

📦 llama.cpp
🏷 Category: AI
🔖 Version: b9484
📅 Released: 2026-06-02 22:00 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

opencl: use flat variants of q4K and q6K gemv for very large M (#24006)

</details>

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

🚀 New Release Alert!

📦 claude-code
🏷 Category: Community Suggested
🔖 Version: v2.1.161
📅 Released: 2026-06-02 21:58 UTC
📊 Assets: 10 files

📝 What's New:
## What's changed

- OTEL_RESOURCE_ATTRIBUTES values are now included as labels on metric datapoints, so you can slice usage metrics by custom dimensions like team or repo
- claude agents rows now show done/total before the detail when work is fanned out; peek shows the longest-running item
- /mcp now collapses claude.ai connectors you've never signed in to behind a "Show unused connect...

🔗 View on GitHub
📥 Download Release

🚀 New Release Alert!

📦 v2rayNG
🏷 Category: Community Suggested
🔖 Version:
📅 Released: 2026-06-02 10:46 UTC
📊 Assets: 10 files

📝 What's New:
### 警告：将在 2026.8.1 禁用跳过证书验证 "allowInsecure" ，请尽快改用证书指纹。到期后无法使用。

### 关于 跳过证书验证 allowInsecure 参数被移除的说明

### 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
- 移除 allowInsecure 首选项，该选项已被弃用，请使用证书指纹 pinnedPeerCertSha256
- Xray-core v26.6.1
📥 Download Release

🚀 New Release Alert!

📦 Ollama
🏷 Category: AI
🔖 Version: v0.30.2
📅 Released: 2026-06-03 00:37 UTC
📊 Assets: 17 files

📝 What's New:
## What's Changed
feat(launch): show and auto-install Cline CLI by @hoyyeva in https://github.com/ollama/ollama/pull/16402
log template details to aid troubleshooting by @dhiltgen in https://github.com/ollama/ollama/pull/16403
cmd/launch: add Qwen code integration by @hoyyeva in https://github.com/ollama/ollama/pull/15900
launch: fix opencode local model limits by @dhiltgen in https...

🔗 View on GitHub
📥 Download Release

🚀 New Release Alert!

📦 llama.cpp
🏷 Category: AI
🔖 Version: b9487
📅 Released: 2026-06-03 06:25 UTC
📊 Assets: 20 files

📝 What's New:
<details open>

update BoringSSL to 0.20260526.0 (#23794)

</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: b9489
📅 Released: 2026-06-03 11:22 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

cuda: reserve space for quantize kv-cache at startup (#23907)

cuda: reserve space for quantize kv-cache at startup

address review comments

remove forward decl

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

remove assert in ggml-cuda.cu

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

</details>

...

🔗 View on GitHub
📥 Download Release

🚀 New Release Alert!

📦 llama.cpp
🏷 Category: AI
🔖 Version: b9490
📅 Released: 2026-06-03 11:46 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

ggml-cpu: use runtime SVE width in FWHT (#24059)

</details>

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

🚀 New Release Alert!

📦 Deno
🏷 Category: Runtime
🔖 Version: v2.8.2
📅 Released: 2026-06-03 13:41 UTC
📊 Assets: 44 files

📝 What's New:
### 2.8.2 / 2026.06.03

- feat(compile): improve --bundle dependency resolution and add --minify
(#34536)
- feat(compile): scope --bundle npm embed to packages actually reached (#34532)
- feat(ext/crypto): add ChaCha20-Poly1305, SHAKE, cSHAKE, TurboSHAKE, SHA-3 HMAC
(#34417)
- feat(ext/crypto): add ML-DSA (FIPS 204) post-quantum signatures (#34448)
- feat(ext/crypto): implement ML-K...

🔗 View on GitHub
📥 Download Release

🚀 New Release Alert!

📦 Transformers
🏷 Category: Machine Learning
🔖 Version: Release v5.10.1
📅 Released: 2026-06-03 15:37 UTC
📊 Assets: 0 files

📝 What's New:
# Release v5.10.1
v5.10.0 was yanked as we publish on a corrupted branch. Sorry everyone, this happens when we rush a release!!!

## New Model additions

### Gemma4 unified+ Gemma4 MTP
<img width="2000" height="400" alt="image" src="https://github.com/user-attachments/assets/5e3ee940-f78d-4343-ac7a-889930800aa6" />

Gemma 4 12B Unified is an encoder-free multimodal model with pretr...

🔗 View on GitHub
📥 Download Release

🚀 New Release Alert!

📦 Astro
🏷 Category: Frontend Framework
🔖 Version: astro@6.4.4
📅 Released: 2026-06-03 17:37 UTC
📊 Assets: 0 files

📝 What's New:
### Patch Changes

- #16926 `1b39ae8` Thanks @narendraio! - Prevents App.match() from throwing on request paths that contain an invalid percent-sequence.

- #16924 `2c0bc94`...

🔗 [View on GitHub
📥 Download Release

🚀 New Release Alert!

📦 llama.cpp
🏷 Category: AI
🔖 Version: b9496
📅 Released: 2026-06-03 20:23 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

mtmd: fix Gemma 4 unified FPE (#24088)

</details>

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

🚀 New Release Alert!

📦 claude-code
🏷 Category: Community Suggested
🔖 Version: v2.1.162
📅 Released: 2026-06-03 21:31 UTC
📊 Assets: 10 files

📝 What's New:
## What's changed

- claude agents --json now includes waitingFor showing what a waiting session is blocked on (e.g. permission prompt)
- --tools: explicitly listing Grep/Glob now provides the dedicated search tools on native builds with embedded search (previously these names were silently ignored)
- /effort now confirms when your chosen level will persist as the default for new sessio...

🔗 View on GitHub
📥 Download Release

🚀 New Release Alert!

📦 llama.cpp
🏷 Category: AI
🔖 Version: b9500
📅 Released: 2026-06-04 06:33 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

metal : reduce rset heartbeat from 500ms -> 5ms (#24074)

</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: b9503
📅 Released: 2026-06-04 10:14 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

fix(mtmd): handle Gemma 4 audio projector embedding size (#24091)

mtmd: handle Gemma 4 audio projector embedding size

rm projectiondim from clipnmmprojembd

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>

</details>

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

🚀 New Release Alert!

📦 llama.cpp
🏷 Category: AI
🔖 Version: b9505
📅 Released: 2026-06-04 11:31 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

server : add header to tools/server/server-http.h (#24089)

</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: b9512
📅 Released: 2026-06-04 15:13 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

return filter to save memory (#24125)

Co-authored-by: lvyichen <lvyichen@stepfun.com>

</details>

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

🚀 New Release Alert!

📦 Exclave
🏷 Category: Community Suggested
🔖 Version: 0.17.43
📅 Released: 2026-06-04 16:03 UTC
📊 Assets: 4 files

📝 What's New:
Compared to 0.17.41

- Rename the "custom v2ray-core fork" used by Exclave to exclave-core. Exclave has never been a de facto v2ray-core client, and Exclave is no longer a nominal v2ray-core client from now on.
- Add Hysteria 2 "Gecko" obfuscation.
- Update mieru to v3.33.0 ("add heartbeat jitter to make traffic analysis harder").
- Fix TrustTunnel uTLS fingerprint ignored.
- Remove "...

🔗 View on GitHub
📥 Download Release

🚀 New Release Alert!

📦 llama.cpp
🏷 Category: AI
🔖 Version: b9518
📅 Released: 2026-06-04 17:13 UTC
📊 Assets: 21 files

📝 What's New:
<details open>

server : disable on-device spec checkpoints (#24108)

</details>

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

🚀 New Release Alert!

📦 Svelte
🏷 Category: Frontend Framework
🔖 Version: svelte@5.56.2
📅 Released: 2026-06-04 20:33 UTC
📊 Assets: 0 files

📝 What's New:
### Patch Changes

- fix: properly track effect end node for async sibling component (#18371)

- fix: prevent false-positive reactivity loss warning (#18373)

- chore: bump esrap dependency (#18372)

- fix: ignore declaration tags for animati...

🔗 View on GitHub
📥 Download Release