RepoJournal
Local LLMs

Local LLMs

Ollama, llama.cpp, vLLM, and SGLang - running and serving open models locally

Keep up with Local LLMs in about 3 minutes a day: what actually shipped — the commits, pull requests, releases, and security advisories that matter.

One email a day. Unsubscribe in one click.

Pick a date

  1. Sun 26 jul
  2. Mon 27 jul
  3. Tue 28 jul
  4. Wed 29 jul
  5. Thu 30 jul
  6. Fri 31 jul
  7. Sat 1 aug
  8. Sun 2 aug
  9. Mon 3 aug
  10. Tue 4 aug
  11. Wed 5 aug
  12. Thu 6 aug
  13. Fri 7 aug
  14. Sat 8 aug
  15. Sun 9 aug
  16. Mon 10 aug
  17. Tue 11 aug
  18. Wed 12 aug
  19. Thu 13 aug
  20. Fri 14 aug
  21. Sat 15 aug
  22. Sun 16 aug
  23. Mon 17 aug
  24. Tue 18 aug
  25. Thu 20 aug
  26. Fri 21 aug
  27. Sat 22 aug
  28. Sun 23 aug
  29. Mon 24 aug
  30. Today 25 aug
Topics: Local LLMs AI / ML Full archive →

The Wire · Showcase

OLLAMA BOLSTERS CLAUDE DESKTOP, VLLM HARDENS AUDIO PATHS

By RepoJournal · Filed · About Local LLMs

hoyyeva ParthSareen Juan Pérez de Algaba mickqian ispobock Georgi Gerganov YiChen Lv
12 people shipped this
hoyyeva @hoyyeva 3 cited ParthSareen @ParthSareen 2 cited Juan Pérez de Algaba @jperezdealgaba 2 cited mickqian @mickqian 2 cited ispobock @ispobock 2 cited Georgi Gerganov @ggerganov 1 cited YiChen Lv @forforever73 1 cited Saad Ali @NIXKnight 1 cited Harry Mellor @hmellor 1 cited Jee Jee Li @jeejeelee 1 cited Jiminator @Jiminator 1 cited Ning Xie @andyxning

Ollama's desktop app just made Claude Desktop integration faster and safer to manage, while vLLM closed a security gap on audio file size limits.

Ollama is tightening its Claude Desktop experience with three fixes: explicit model mappings [1], a default-on Auto mode [2], and faster toggle responsiveness [3] that replaces blocking model checks with a lightweight connection summary. The same team also killed a duplicated first-use modal and a stale integration chevron [4], with a scrollable integrations list to match [5]. Across the stack, llama.cpp shipped a ccache-clear tweak [6] to prevent CI cache rot, a per-device FlashAttention tuning table for Metal [7], and a grammar fix that makes hyphens literal in character classes [8], so tool-call grammars stop failing on escaped dashes. vLLM now enforces VLLM_MAX_AUDIO_CLIP_FILESIZE_MB on every audio path [9], a security fix worth shipping before you touch any multimodal pipeline, and documents the UUID exposure risk that comes with it [10]. Model cleanup continues: vLLM removes ten deprecated architectures [11] and deprecated parameters [12], so plan a migration if you rely on any of them. SGLang fixed a nasty decode retraction bug that could resume a request on someone else's recurrent state [13], and added a test for MXFP8 KV state transfer on Inkling [14]. It also lands GGUF and NVFP4 support for MiniMax H3 diffusion [15] [16], plus docs that split Qwen3.8-27B NVFP4 export cells by lm_head precision into two checkpoints [17].

One email a day. Unsubscribe in one click.

Action items

References

  1. [1] app: add Claude Desktop model mappings ↗ ollama/ollama
  2. [2] app: add Claude Desktop Auto mode setting ↗ ollama/ollama
  3. [3] app: improve desktop integration responsiveness ↗ ollama/ollama
  4. [4] app: fix desktop interaction regressions ↗ ollama/ollama
  5. [5] app: make integrations list scrollable ↗ ollama/ollama
  6. [6] ci : apply ccache-clear with older/min/dry-run to all ccache jobs ↗ ggml-org/llama.cpp
  7. [7] metal : per-device tuned (Q, NE) for flash-attn vec (#26570) ggml-org/llama.cpp
  8. [8] grammar : parse \- in char classes as literal hyphen (#27591) ggml-org/llama.cpp
  9. [9] fix(security): enforce VLLM_MAX_AUDIO_CLIP_FILESIZE_MB on all audio paths (#53561) vllm-project/vllm
  10. [10] [Docs][Security] Document multimodal media UUID security implications (#53582) vllm-project/vllm
  11. [11] [Model] Remove ten deprecated model architectures (#53608) vllm-project/vllm
  12. [12] [MISC] Cleanup deprecated parameters (#53559) vllm-project/vllm
  13. [13] Fix recurrent state loss on decode retraction ↗ sgl-project/sglang
  14. [14] Add PD test for inkling with mxfp8 KV ↗ sgl-project/sglang
  15. [15] [Diffusion] Load MiniMax H3 GGUF text encoders ↗ sgl-project/sglang
  16. [16] [Diffusion] Load Comfy NVFP4 MiniMax H3 checkpoints ↗ sgl-project/sglang
  17. [17] [docs] Split the Qwen3.8-27B NVFP4 cells by lm_head precision ↗ sgl-project/sglang

Quick answers

What shipped in Local LLMs on August 25, 2026?
Ollama's desktop app just made Claude Desktop integration faster and safer to manage, while vLLM closed a security gap on audio file size limits. In total, 110 commits, 110 pull requests, and 9 releases landed.
Who contributed to Local LLMs on August 25, 2026?
12 developers shipped this update, including hoyyeva, ParthSareen, Georgi Gerganov, YiChen Lv, Saad Ali, Juan Pérez de Algaba, Harry Mellor, and Jee Jee Li, and 4 more.
What were the notable Local LLMs updates?
app: add Claude Desktop model mappings, app: add Claude Desktop Auto mode setting, and app: improve desktop integration responsiveness.

More from Local LLMs

Local LLMs Local LLMs

VLLM'S P2P WEIGHT SYNC CUTS RL MOE TRANSFER COSTS

Forget all-gathering experts during RL rollout: vLLM's new sharded_rdt backend lets each worker pull only the slice it needs, turning a total_bytes transfer into a total_bytes divided by num_workers one.

allozaur gaugarg-nv am17an cabelo +9
llms 180 shipped
Local LLMs Local LLMs

SGLang Fixes Pixtral 500s as vLLM Cuts TTFT 25%

The biggest news overnight: SGLang is patching a production-breaking Pixtral bug, and vLLM engineers found a way to shave up to 25% off time-to-first-token on Mamba models.

CISC ngxson Kartik Sirohi superm1 +7
llms 134 shipped
Local LLMs Local LLMs

SGLang ships v0.5.18 with 710 PRs and DeepSeek V4 FP4 auto-routing

The biggest release of the week just landed: SGLang v0.5.18 adds new models, fixes a silent disagg bug, and defaults DeepSeek V4 FP4 checkpoints to the right MoE runner.

ParthSareen hoyyeva jessegross Todd Malsbary +11
llms 266 shipped
Local LLMs Local LLMs

DeepSeek V4 fuses shared experts, as vLLM ships a security guard

The biggest local-LLM repos are moving fast: DeepSeek V4's MoE kernel gets a massive fusion, while vLLM patches a security hole.

ParthSareen hoyyeva dhiltgen Alexander Heisler +12
llms 274 shipped

Daily updates, in your inbox

Follow Local LLMs

Keep up with Local LLMs in about 3 minutes a day: what actually shipped — the commits, pull requests, releases, and security advisories that matter.

or

One email a day. Unsubscribe in one click. Read a past issue →

Elsewhere on the wire

AI Agents AI Agents

CLINE'S SEARCH TOOL HAD A MEMORY HOLE THAT CRASHED THE AGENT

A single-line JSON file could OOM your entire Cline agent, and the fix shipped last night in a string of hotfixes.

github-actions[bot] dependabot eyurtsev langchain-oss-model-profiles[bot] +6
ai-agents 62 shipped
CachyOS @CachyOS

Faugus Launcher v2.x Dependencies Fixed

Fresh installs of Faugus Launcher crashed with a missing Adw namespace, and the fix just landed.

skare1412 witchlliee chaopeng Antiz96 +9
infra 87 shipped
Elixir & Phoenix Elixir & Phoenix

LiveView crash fix lands as Elixir corrects Greek casing

Phoenix LiveView patches a stale-diff crash while Elixir fixes final sigma casing in Greek strings.

AlexGx Barna Kovacs José Valim Łukasz Samson +1
elixir 20 shipped
Mobile platforms Mobile platforms

Flutter Ships Release-Mode Route Injection as Swift and Kotlin Rush to Harden Compilers

Flutter's release-mode route injection fixes a long-standing Android gap, while Swift and Kotlin land compiler stability fixes that will save you from cryptic crashes.

Camille Simon Reid-Agent Victoria Ashworth dcharkes +8
mobile 144 shipped
Want every project, not just this one?