Xuan-Son Nguyen

@ngxson ↗ first byline July 2026

Every morning, RepoJournal's newsroom reads what shipped across the open-source projects developers depend on — and writes the wire. Your commits kept making the news. This is your clippings file: the stories where your work was the story.

stories filed

daily wires

$ grep -rn "author: ngxson" wires/ | sort -r

Local LLMs

wire 2026-10-05

vLLM 0.31.0 ships DeepSeek-V4.1-Flash kernels, streaming errors stop vanishing behind DONE

llama: support both embd + raw tokens in batch ggml-org/llama.cpp

Local LLMs

wire 2026-09-12

Ollama drops its CLI agent, llama.cpp cuts build times, vLLM fixes crash under DP>1

server: refactor subproc handling (#28555) ggml-org/llama.cpp
server: refactor subproc handling ggml-org/llama.cpp

Local LLMs

wire 2026-09-06

vLLM closes scale-out multimodal handoff hole

common: add --log-jsonl (#28437) ggml-org/llama.cpp

Local LLMs

wire 2026-08-28

LLAMA.CPP UNLEASHES QWEN3.8-FLASH-NEXT SUPPORT

quantize: cap working memory size to avoid loading big tensors onto RAM ggml-org/llama.cpp
llama: model_loader: add TENSOR_READ_LAZY ggml-org/llama.cpp

Local LLMs

wire 2026-08-16

LLAMA.CPP OVERHAULS INFERENCE FLAGS, VLLM PATCHES DEEPSEEK SPARSE MLA

server: re-design yield_to_queue thread model ggml-org/llama.cpp

Local LLMs

wire 2026-08-14

OLLAMA LAUNCHES DEEPSEEK AND MUSE INTEGRATIONS WHILE VLLM SHIPS HARDWARE-AGNOSTIC MODELING

server: refactor + correctness fixes for metrics ggml-org/llama.cpp

Local LLMs

wire 2026-08-12

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

mtmd: support pocket-tts (#26871) ggml-org/llama.cpp

Local LLMs

wire 2026-08-08

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

server: (router) add LRU scheduler ggml-org/llama.cpp
mtmd: fix longest_edge ignoring min/max pixels ggml-org/llama.cpp

Local LLMs

wire 2026-08-05

OLLAMA FIXES RACE CONDITIONS AS LLAMA.CPP SHIPS BREAKING TTS CHANGES

mtmd: support Qwen3-TTS (note: breaking change to llama-tts binary) (#26254) ggml-org/llama.cpp

Local LLMs

wire 2026-08-04

OLLAMA REWIRES OPENAI COMPATIBILITY, LLAMA.CPP HARDENS SAMPLING

server: add get_info tool (#26522) ggml-org/llama.cpp

Local LLMs

wire 2026-07-26

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

server: support MCP stdio ggml-org/llama.cpp