$ git log --author="mickqian" --all --oneline

On the record

mickqian

@mickqian ↗ 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: mickqian" wires/ | sort -r

Local LLMs

wire 2026-10-14

llama.cpp server stack overflow, Ollama brings Metal kernels to CUDA

[diffusion] Replay small Triton wrappers' launches per operand signature sgl-project/sglang

Local LLMs

wire 2026-10-11

MiniCPM-V 4.7 lands in llama.cpp, vLLM fixes KV reservation under pressure

[diffusion] torch.compile: keep the TP all-reduce inside the graph sgl-project/sglang
[diffusion] BCG: warn instead of disabling on unvalidated models sgl-project/sglang

Local LLMs

wire 2026-09-14

SYCL memory reporting fixed, sparse-attention kernels land across vLLM and SGLang

[Diffusion] Make the SP sequence gather pass contiguous shards sgl-project/sglang

Local LLMs

wire 2026-09-13

vLLM EngineCore can be killed by crafted stop_token_ids, llama.cpp reworks JSON schema handling

[Diffusion] Pick the attention backend by measuring it sgl-project/sglang

Local LLMs

wire 2026-09-07

Vulkan adds TQ1_0, Spark2.5 lands in llama.cpp

[diffusion] fix: quiet internal warmup frame searches sgl-project/sglang

Local LLMs

wire 2026-09-04

Ollama enables speculative decoding under structured output, vLLM adds LoRA and fusion

[diffusion] Compose third-party component bundles safely sgl-project/sglang

Local LLMs

wire 2026-08-25

OLLAMA BOLSTERS CLAUDE DESKTOP, VLLM HARDENS AUDIO PATHS

[Diffusion] Load MiniMax H3 GGUF text encoders sgl-project/sglang
[Diffusion] Load Comfy NVFP4 MiniMax H3 checkpoints sgl-project/sglang

Local LLMs

wire 2026-08-23

SGLang Fixes Pixtral 500s as vLLM Cuts TTFT 25%

[diffusion] optimization: transfer mapped layers through a courier thread sgl-project/sglang

Local LLMs

wire 2026-08-16

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

feat: add safeguards for remote media URLs sgl-project/sglang
fix(diffusion): scope attention backend fallback sgl-project/sglang

Local LLMs

wire 2026-08-12

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

Fix model-driven DiT layerwise offload auto policy sgl-project/sglang

Local LLMs

wire 2026-07-29

OLLAMA RIPS OUT IMAGE GENERATION, LLAMA.CPP SHIPS SPECULATIVE DECODING

fix(vlm): reject Moss vision metadata mismatches sgl-project/sglang

Local LLMs

wire 2026-07-27

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

model: support EmbeddingGemma sgl-project/sglang

Local LLMs

wire 2026-07-26

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

[Performance] Speed up Marlin MoE with occupancy-aware launch specialization sgl-project/sglang