$ git log --author="jessegross" --all --oneline
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.
27
stories filed
15
daily wires
$ grep -rn "author: jessegross" wires/ | sort -r
MLX engine graduates out of x/, ROCm fixes silent attention corruption
- Move the MLX engine out of x/ ollama/ollama
- cmd: launch the MLX runner without the engine dispatcher ollama/ollama
Ollama fixes unbounded KV memory growth, vLLM clarifies CVE timing
- mlx: scope array lifetimes instead of pinning and sweeping ollama/ollama
- mlxrunner: Evict prefix cache snapshots from the active conversation ollama/ollama
- mlxrunner: keep the reused head of a cached edge safe from eviction ollama/ollama
- mlx: drop the empty-handle checks outside the bindings ollama/ollama
Ollama enables speculative decoding under structured output, vLLM adds LoRA and fusion
Error propagation hardened in ollama's MLX bindings, gemma4 gains multimodal support
- mlxrunner: capture MLX errors in a single buffer read after every call ollama/ollama
- mlxrunner: check every fallible mlx-c call in the MLX bindings ollama/ollama
- gemma4: image and audio input on the MLX engine ollama/ollama
- gemma4: image and audio input support ollama/ollama
vLLM 0.28.0 LANDED WITH 584 COMMITS AND A KIMI-K3 PERFORMANCE PUSH
- mlx: remove the text-only gemma3 model ollama/ollama
OLLAMA'S MLX RUNNER NOW SPEAKS STRUCTURED OUTPUT
- mlxrunner: add structured output support ollama/ollama
- llm: remove the unused Grammar completion-request field ollama/ollama
SGLang ships v0.5.18 with 710 PRs and DeepSeek V4 FP4 auto-routing
OLLAMA CUTS REPEAT PENALTY BLOAT, LLAMA.CPP SHIPS POCKET-TTS SUPPORT
OLLAMA SHIPS VISION SUPPORT ACROSS MLX AND QWEN3.5 AS LLAMA.CPP FIXES DISPATCH BUGS
- mlxrunner: Add image input support ollama/ollama
- mlxrunner: reject media requests the model cannot serve ollama/ollama
- qwen3_5: image input support ollama/ollama
- mlxrunner: expand image tags into placeholder tokens ollama/ollama
OLLAMA SHIPS BLOCK-DIFFUSION SPECULATIVE DECODING, SGLANG LAUNCHES KIMI K3 DAY-0
OLLAMA FIXES KV CACHE CORRUPTION, LLAMA.CPP HARDENS FILE SEARCH, VLLM KILLS MOE LEGACY CODE
QWEN3.5 SPECULATIVE DECODING HITS 70% SPEEDUP ON LLAMA.CPP, OLLAMA ROUTES CLOUD MODELS
- mlx: qwen3.5 MTP speculative decoding ollama/ollama
OLLAMA CLEANS UP LINT PIPELINE AS LLAMA.CPP ADDS SPECULATIVE DRAFTING FOR GLM-5.2
LLAMA.CPP SHIPS FIVE RELEASES IN 24 HOURS, FIXES SPECULATIVE DECODING ACROSS THE STACK
A page like this — but yours, daily.
These clippings exist because your work kept showing up in other projects' wires. RepoJournal can write the whole journal: your commits, PRs and releases, turned into a daily devlog you never have to write.
Free. We read your public contributions only - private repos are never summarised.