Who contributed to Local LLMs on July 27, 2026?

14 developers shipped this update, including github-actions[bot], dhiltgen, timkhronos, Pascal, AndreasKaratzas, walterbm, edwinlim0919, and zxd1997066, and 6 more.

What were the notable Local LLMs updates?

v0.32.5, model: Add MiniMax-M3 (MSA: MiniMax Sparse Attention) support (#24908), and ui: detect the conversation import format from file contents (#26121).

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

LLAMA.CPP SHIPS MINIMAX-M3 SPARSE ATTENTION, VLLM UNLOCKS HETEROGENEOUS PREFILL-DECODE

By RepoJournal · Filed 07:01 UTC on July 27, 2026 · About Local LLMs

14 people shipped this

timkhronos @timkhronos 3 cited

Pascal @ServeurpersoCom 2 cited

github-actions[bot] @github-actions[bot] 1 cited

edwinlim0919 @edwinlim0919 1 cited

yushengsu-thu @yushengsu-thu 1 cited

mickqian @mickqian 1 cited

dhiltgen @dhiltgen

AndreasKaratzas @AndreasKaratzas

walterbm @walterbm

zxd1997066 @zxd1997066

The inference stack gets a new model architecture and a fundamental shift in how prefill and decode can run on different hardware configurations.

Llama.cpp landed full MiniMax-M3 support [2] [4] with vision tower integration, adding sparse attention capability to handle 60-layer, 128-expert MoE models where "a lightweight per-GQA-group indexer scores the visible causal context, max-pools the scores into 128-token key blocks, and selects the top-16 blocks" [6]. The model joins an expanding list of specialized architectures getting native dispatch. On the vLLM side, MoRIIO heterogeneous prefill-decode routing [7] is now live, enabling prefill and decode phases to run different parallelism strategies (TP vs DP+DP) on the same cluster, yielding measurably higher throughput and lower TTFT at scale on MI300X. SGLang shipped LoRA support under breakable CUDA graphs [8], restoring prefill graph acceleration to LoRA workloads, and added EmbeddingGemma [9] with bidirectional attention and mean pooling. Meanwhile, llama.cpp fixed critical routing bugs for model names with slashes [5], resolved iOS conversation import by detecting format from file contents [3], and Ollama pushed an mlx update [1]. This period saw 60 commits and 60 PRs across 4 core repos, with 5 releases shipping.

Action items

→ Pull vLLM to enable heterogeneous prefill-decode if running mixed TP/DP clusters at high concurrency vllm-project/vllm [plan]
→ Update llama.cpp if serving models with slash-containing names (router mode) ggml-org/llama.cpp [immediate]
→ Upgrade SGLang if running LoRA inference; prefill graphs now work sgl-project/sglang [plan]

References

[1] v0.32.5 ↗ ollama/ollama
[2] model: Add MiniMax-M3 (MSA: MiniMax Sparse Attention) support (#24908) ggml-org/llama.cpp
[3] ui: detect the conversation import format from file contents (#26121) ggml-org/llama.cpp
[4] mtmd: Add Vision Support for Minimax-M3 (#25113) ggml-org/llama.cpp
[5] server + ui: fix stream routes for model names containing a slash (#26137) ggml-org/llama.cpp
[6] Add MiniMax-M3 (MSA: MiniMax Sparse Attention) support ↗ ggml-org/llama.cpp
[7] [Core][KV-transfer] MoRIIO: heterogeneous TP<->DP prefill/decode read routing ↗ vllm-project/vllm
[8] [LoRA] Support LoRA under the breakable/full prefill CUDA graph ↗ sgl-project/sglang
[9] model: support EmbeddingGemma ↗ sgl-project/sglang

Quick answers

What shipped in Local LLMs on July 27, 2026?: The inference stack gets a new model architecture and a fundamental shift in how prefill and decode can run on different hardware configurations. In total, 60 commits, 60 pull requests, and 5 releases landed.
Who contributed to Local LLMs on July 27, 2026?: 14 developers shipped this update, including github-actions[bot], dhiltgen, timkhronos, Pascal, AndreasKaratzas, walterbm, edwinlim0919, and zxd1997066, and 6 more.
What were the notable Local LLMs updates?: v0.32.5, model: Add MiniMax-M3 (MSA: MiniMax Sparse Attention) support (#24908), and ui: detect the conversation import format from file contents (#26121).

LLAMA.CPP LOCKS DOWN WASM, ADDS MCP STDIO, HEXAGON GETS IM2COL ACCELERATION

llama.cpp disabled OpenMP for Emscripten builds to fix WASM compilation, while shipping full MCP stdio support and unlocking 1.5x to 3.5x latency gains on Hexagon vision models.

llms 139 shipped 2-min read

Local LLMs 3 days ago

OLLAMA LANDS LAGUNA SUPPORT AND CRUSHES MEMORY LEAKS WHILE SGLANG HITS V0.5.16 WITH CONFIDENCE-DRIVEN SPECULATIVE DECODING

Ollama shipped three critical performance and reliability fixes for Metal residency and concurrent access patterns, while SGL-Lang released 0.5.16 with a new speculative algorithm hitting 383.7 tok/s on DeepSeek-V4.

+11

llms 210 shipped 2-min read

Local LLMs 4 days ago

LLAMA.CPP SHIPS FIVE RELEASES IN 24 HOURS, FIXES SPECULATIVE DECODING ACROSS THE STACK

The inference stack is consolidating around speculative decoding, and the bugs surfacing there are getting squashed across three major projects simultaneously.

llms 157 shipped 2-min read

Local LLMs 5 days ago

OLLAMA AGENTS NOW IMPORT SKILLS FROM CODEX AND CLAUDE

Ollama shipped a skills import system that lets coding agents pull validated skill directories from external sources, while simultaneous fixes to GLM tool-call parsing and Laguna model alignment prevent agents from silently failing.

+10

llms 212 shipped 2-min read

Elsewhere on the wire

AI Agents about 22 hours ago

CLINE SHIPS FIVE CRITICAL AGENT FIXES AFTER END-TO-END TESTING BLITZ

Saoudrizwan just landed a cascade of fixes that prevent the agent loop from running wild, stop file reads from resolving to the wrong directory, and plug the compaction pipeline.

ai-agents 16 shipped 2-min read

@CachyOS about 22 hours ago

GLIBC 2.43 REBUILD SHIPS, INSTALLER JUMPS TO C++26

CachyOS pushed glibc 2.43 through the pipeline while the CLI installer upgraded its C++ standard to C++26, signaling a major refresh across core infrastructure.

infra 97 shipped 1-min read

Elixir & Phoenix about 22 hours ago

ECTO FIXES SUBQUERY PLANNING IN JOINS, ELIXIR PATCHES IEX PARSING

Ecto's query planner now handles subqueries correctly in interpolated join filters, while Elixir fixes a syntax error that broke 'not in' as a continuation operator in IEx.