Who contributed to Local LLMs on August 10, 2026?

13 developers shipped this update, including jessegross, Daniel Hiltgen, github-actions[bot], allozaur, yomaytk, Caleb DeLeeuw, zexplorerhj, and R3hankhan123, and 5 more.

What were the notable Local LLMs updates?

mlxrunner: Add image input support, mlxrunner: reject media requests the model cannot serve, and qwen3_5: image input support.

Local LLMs

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

Pick a date

Topics: Local LLMs AI / ML Full archive →

The Wire · Showcase

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

By RepoJournal · Filed 07:00 UTC on August 10, 2026 · About Local LLMs

13 people shipped this

jessegross @jessegross 4 cited

github-actions[bot] @github-actions[bot] 2 cited

ch-wan @ch-wan 2 cited

zexplorerhj @zexplorerhj 1 cited

R3hankhan123 @R3hankhan123 1 cited

aoshen02 @aoshen02 1 cited

hnyls2002 @hnyls2002 1 cited

Daniel Hiltgen @dhiltgen

allozaur @allozaur

yomaytk @yomaytk

Caleb DeLeeuw @SolshineCode

Srinivasoo7 @Srinivasoo7

thegoldenflow @thegoldenflow

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

Jesse Gross landed the core vision infrastructure for Ollama's MLX backend [1], which expands image tags into placeholder tokens during prepare and routes media through a new media interface that keeps the runner agnostic to model-specific image layouts [4]. Companion work adds Qwen3.5 vision support with interleaved rope positions and causal image expansions that split prefill chunks [3], while a guard prevents models without media capability from crashing on image requests [2]. On the inference engine side, llama.cpp shipped two rapid releases fixing CPU dispatch bugs: the Q5_0 path in SpaceMiT backend [5] and removal of the deprecated HIP ROCWMMA flag [6]. Across 80 commits and 75 PRs in this period, vLLM merged quantization coverage for Ling 3.0 Flash FP8 [7], enabled GPTQ and AWQ on IBM Z s390x architecture [8], and fixed a critical single-node startup race where competing processes could claim rendezvous ports, causing EADDRINUSE failures [9]. SGLang hardened speculative decoding against KV corruption when draft tokens exceed 4 [10] and refactored config reading to respect post-publish overrides across the KV-cache, runner, and scheduler paths [11], [12].

Action items

→ If serving Ollama MLX models with images: pull the latest runner code and validate that unsupported models fail gracefully ollama/ollama [plan]
→ If running vLLM single-node executors: upgrade to fix the port race that causes startup hangs vllm-project/vllm [immediate]
→ If using SGLang with speculative decoding: pull the KV corruption fix before deploying with >4 draft tokens sgl-project/sglang [immediate]
→ Monitor llama.cpp b10333+ releases for backend-specific dispatch fixes ggml-org/llama.cpp [monitor]

References

[1] mlxrunner: Add image input support ↗ ollama/ollama
[2] mlxrunner: reject media requests the model cannot serve ollama/ollama
[3] qwen3_5: image input support ollama/ollama
[4] mlxrunner: expand image tags into placeholder tokens ollama/ollama
[5] b10333 ↗ ggml-org/llama.cpp
[6] b10332 ↗ ggml-org/llama.cpp
[7] `[Model][Quantization] Add Ling-3.0-flash-fp8 support` ↗ vllm-project/vllm
[8] [CPU] Enable GPTQ and AWQ quantization for s390x ↗ vllm-project/vllm
[9] [BugFix] Use file:// rendezvous for single-node executors to eliminate startup port races ↗ vllm-project/vllm
[10] [DSV4] Fix silent KV corruption when speculative draft tokens > 4 ↗ sgl-project/sglang
[11] config: the KV-cache configurator reads the bags ↗ sgl-project/sglang
[12] config: the runner and scheduler read resolved config from the bags ↗ sgl-project/sglang

Quick answers

What shipped in Local LLMs on August 10, 2026?: Ollama's MLX runner now processes images natively, preserving prefix caching and speculative decoding while rejecting unsupported requests with clear errors. In total, 80 commits, 75 pull requests, and 2 releases landed.
Who contributed to Local LLMs on August 10, 2026?: 13 developers shipped this update, including jessegross, Daniel Hiltgen, github-actions[bot], allozaur, yomaytk, Caleb DeLeeuw, zexplorerhj, and R3hankhan123, and 5 more.
What were the notable Local LLMs updates?: mlxrunner: Add image input support, mlxrunner: reject media requests the model cannot serve, and qwen3_5: image input support.

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

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.

+11

llms 271 shipped

Local LLMs Aug 9

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.

llms 102 shipped

Local LLMs Aug 8

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.

+12

llms 263 shipped

Local LLMs Aug 7

LLAMA.CPP HARDENS VULKAN STACK, VLLM CUTS ATTENTION LATENCY, SGLANG SCALES MLA

Vulkan submission batching and AMD ROCm CI fixes land in llama.cpp as vLLM optimizes attention kernels and sglang adds per-request MLA scheduling.

llms 231 shipped

Elsewhere on the wire

AI Agents Aug 11

LANGCHAIN PATCHES TOOL CALLS, OPENHANDS SURFACES HIDDEN INTEGRATIONS

LangChain's OpenAI wrapper shipped a fix for invalid tool calls that were silently dropped, while OpenHands surfaced integrations the automation layer was burying.

ai-agents 44 shipped

@CachyOS Aug 11

CACHYOS LINUX 7.1.8 SHIPS WITH VMALLOC OPTIMIZATIONS; NOCTALIA CONFIG UPDATED FOR BETA 8

CachyOS Linux 7.1.8 landed overnight with upstream rebase and performance tuning across memory allocation, while Noctalia configuration hardened for beta 8 stability with direct_scanout gaming support.

infra 83 shipped

Elixir & Phoenix Aug 11

PHOENIX LIVE VIEW PATCHES OPEN REDIRECT VULNERABILITY ACROSS TWO VERSIONS

Phoenix Live View shipped emergency security fixes for CVE-2026-64941 in both v1.1.33 and v1.2.9 to close an open redirect hole via ASCII control characters in the redirect/2 function.

elixir 14 shipped

@dotnet Aug 11

BLAZOR TESTING OVERHAUL SHIPS NATIVE AOT HARNESS, ROSLYN REVERTS SONIC SPLIT

ASP.NET Core's Components.Testing library graduates from xUnit to MSTest on Microsoft Testing Platform, while Roslyn backs out its ambitious Sonic declaration/implementation split to unblock the next build.

+10

dotnet 66 shipped

Want every project, not just this one?

Follow Local LLMs