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

The Wire · Showcase

OLLAMA PATCHES CRITICAL PARSER BUG, NEMOTRON 3 LANDS WITH SPECULATIVE DECODING

By RepoJournal · Filed · About Local LLMs

dhiltgen ch-wan Pedro Cuenca superm1 gaugarg-nv khluu Priyjain-amd
15 people shipped this
dhiltgen @dhiltgen 3 cited ch-wan @ch-wan 2 cited Pedro Cuenca @pcuenca 1 cited superm1 @superm1 1 cited gaugarg-nv @gaugarg-nv 1 cited khluu @khluu 1 cited Priyjain-amd @Priyjain-amd 1 cited AndreasKaratzas @AndreasKaratzas 1 cited mmangkad @mmangkad 1 cited Pascal @ServeurpersoCom github-actions[bot] @github-actions[bot] aoshen02 @aoshen02 BugenZhao @BugenZhao Brayden Zhong @b8zhong Khoa Pham @kpham-sgl

Ollama shipped v0.32.7 with a critical fix for boundary token corruption in model invocation, while full MLX support for Nemotron 3 Nano Omni brings self-draft speculation to inference without a separate draft model.

The parser bug [1] hit production when models emit <|message|> boundary tokens in positions that broke ATEM parameter parsing, replacing the expected terminator entirely. The fix replaces strip-after-cut recovery with a unified name-scan path that handles both the terminated and unterminated shapes. In parallel, Nemotron 3 support [2] lands with Metal-optimized quantized expert kernels and a built-in multi-token prediction head that serves as a self-draft speculator, eliminating the need for a separate draft model during speculative decoding. llama.cpp moved fast this cycle: Muse Glimmer architecture support [4] shipped, ROCm 7.14 CI targets [5] are now live, and backend sampling extended from single to multiple outputs per sequence [6], unblocking speculative decoding in the inference engine. vLLM v0.27.0 [7] landed with Kimi K3 full-stack support across core, kernels, Python and Rust frontends, plus CPU Zen MoE routing through zentorch [8] ahead of fallback GEMM paths. SGLang hardened spec-decode testing [9], fixed DSpark shared-expert layout with the DSV4 gate [10], and unified memory now works with PD disaggregation [11] after fixing a NaN logits bug in deterministic Triton extend [12].

One email a day. Unsubscribe in one click.

Action items

References

  1. [1] parsers: recover boundary tokens fumbled into glimmer ATEM invoke names ↗ ollama/ollama
  2. [2] mlx: implement Nemotron 3 ↗ ollama/ollama
  3. [3] Release v0.32.7 ↗ ollama/ollama
  4. [4] model: Muse Glimmer Support (#26841) ggml-org/llama.cpp
  5. [5] Add CI targets for ROCm 7.14 ↗ ggml-org/llama.cpp
  6. [6] Backend sampling multi output ↗ ggml-org/llama.cpp
  7. [7] v0.27.0 ↗ vllm-project/vllm
  8. [8] [CPU][Zen] Route BF16 MoE inference through zentorch on AMD ↗ vllm-project/vllm
  9. [9] [CI] Solidify speculative decoding E2E coverage ↗ vllm-project/vllm
  10. [10] Fix DSV4 DSpark shared expert loading ↗ sgl-project/sglang
  11. [11] [PD] Support --enable-unified-memory with PD disaggregation (kimi-linear MLA hybrid-Mamba) ↗ sgl-project/sglang
  12. [12] Fix NaN logits from deterministic Triton extend on the unified memory pool ↗ sgl-project/sglang

Quick answers

What shipped in Local LLMs on August 11, 2026?
Ollama shipped v0.32.7 with a critical fix for boundary token corruption in model invocation, while full MLX support for Nemotron 3 Nano Omni brings self-draft speculation to inference without a separate draft model. In total, 129 commits, 129 pull requests, and 13 releases landed.
Who contributed to Local LLMs on August 11, 2026?
15 developers shipped this update, including dhiltgen, Pedro Cuenca, Pascal, github-actions[bot], superm1, gaugarg-nv, khluu, and Priyjain-amd, and 7 more.
What were the notable Local LLMs updates?
parsers: recover boundary tokens fumbled into glimmer ATEM invoke names, mlx: implement Nemotron 3, and Release v0.32.7.

More from Local LLMs

Local LLMs Local LLMs

OLLAMA CUTS REPEAT PENALTY BLOAT, LLAMA.CPP SHIPS POCKET-TTS SUPPORT

Ollama kills a decade of default penalty cruft that was drowning every model, while llama.cpp gains multimodal audio chops and vLLM fixes ROCm speculative decoding corruption.

dhiltgen Jesse Gross hoyyeva Xuan-Son Nguyen +11
llms 258 shipped
Local LLMs Local LLMs

OLLAMA SHIPS VISION SUPPORT ACROSS MLX AND QWEN3.5 AS LLAMA.CPP FIXES DISPATCH BUGS

Ollama's MLX runner now processes images natively, preserving prefix caching and speculative decoding while rejecting unsupported requests with clear errors.

jessegross Daniel Hiltgen github-actions[bot] allozaur +9
llms 157 shipped
Local LLMs Local LLMs

OLLAMA CUTS MODEL CONFIG BLOAT 100KB+ PER MODEL, LLAMA.CPP SHIPS TOOL ISOLATION AND CUDA FUSION GAINS

Ollama eliminated redundant manifest data ballooning config blobs on safetensors models, while llama.cpp landed docker-backed tool isolation and fused three GPU kernels into one.

Daniel Hiltgen github-actions[bot] grafail Isotr0py +7
llms 102 shipped
Local LLMs Local LLMs

OLLAMA SHIPS BLOCK-DIFFUSION SPECULATIVE DECODING, SGLANG LAUNCHES KIMI K3 DAY-0

Draft models just got faster: Ollama merged DFlash block-diffusion speculative decoding that proposes entire token sequences in one forward pass, while SGLang shipped production-ready support for Kimi K3, a 2.8T-parameter multimodal LatentMoE that routes through a latent space with 896 experts.

jessegross ParthSareen hoyyeva dhiltgen +12
llms 263 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

LANGCHAIN SHIPS THREE CRITICAL RELEASES IN 12 HOURS, CLOSES SETUPTOOLS VULNERABILITY

LangChain pushed langchain-core 1.5.4, langchain 1.3.15, and langchain-anthropic 1.5.5 overnight while patching a setuptools supply-chain risk that gated the Hugging Face integration.

John Kennedy github-actions[bot] langchain-oss-model-profiles[bot] neubig +9
ai-agents 59 shipped
CachyOS @CachyOS

CACHYOS KERNEL BUMPS TO 7.1.7 AS MIRROR NETWORK EXPANDS

CachyOS shipped kernel 7.1.7 overnight while extending its mirror footprint across Europe and adding Simplified Chinese to the wiki.

Vladislav Nepogodin TriMoon Vasiliy Stelmachenok Wilbur +5
infra 60 shipped
Elixir & Phoenix Elixir & Phoenix

ELIXIR TIGHTENS GUARD SYNTAX, PHOENIX FIXES MIX DETECTION

José Valim shut down a common footgun in Elixir guards while the team fixed a startup bug that breaks when mix is available but not yet started.

José Valim SteffenDE
elixir 6 shipped
.NET @dotnet

BROWSER WASM BLOAT FIXED, RELOCATION SHRINKING SHIPS

dotnet/runtime eliminated unnecessary cryptography dependencies from browser builds while implementing code section relocation optimizations that shrink Wasm binaries.

Copilot copilot-swe-agent adamperlin elinor-fung +4
dotnet 91 shipped
Want every project, not just this one?