ggerganov

@ggerganov ↗ first byline August 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: ggerganov" wires/ | sort -r

Local LLMs

wire 2026-11-08

Metal GROUP_NORM fix, Ripple preview lands in Ollama's MLX runner

metal : fix GROUP_NORM for ne03 > 1 and non-contiguous inputs ggml-org/llama.cpp

Local LLMs

wire 2026-10-25

MoE expert masking lands across every llama.cpp backend

metal : remove mul_mm_id amax rescaling ggml-org/llama.cpp

Local LLMs

wire 2026-10-13

Metal MoE fix for duplicate ids, sglang stops crashing on retracted DeepSeek-V4

metal : fix mul_mat_id with duplicate ids (#30373) ggml-org/llama.cpp

Local LLMs

wire 2026-09-22

vLLM 0.30.0 lands DeepSeek-V4.1-Flash, and a min_tokens validation hole closes

ggml-metal : simplify fusion pattern op list declaration ggml-org/llama.cpp

Local LLMs

wire 2026-09-21

llama.cpp sanitizes invalid UTF-8 in the parser AST

metal : support arbitrary hc in dsv4_hc_pre ggml-org/llama.cpp

Local LLMs

wire 2026-09-20

Metal MoE/SSM fusion lands, MiMo-V2.5 fp8 sharding fixed

metal : add MoE and SSM_CONV fusion optimizations ggml-org/llama.cpp

Local LLMs

wire 2026-09-15

llama.cpp 0.4.1 lands Maple 20B-A1B, Ollama drops typical_p

ggml-cpu : disable PCH and fix CACHE_LINE_SIZE ambiguity to fix heap corruption (#28882) ggml-org/llama.cpp

Local LLMs

wire 2026-09-11

Ollama fixes unbounded KV memory growth, vLLM clarifies CVE timing

tests : drop SYCL special-casing in test-backend-ops.cpp ggml-org/llama.cpp

Local LLMs

wire 2026-08-25

OLLAMA BOLSTERS CLAUDE DESKTOP, VLLM HARDENS AUDIO PATHS

ci : apply ccache-clear with older/min/dry-run to all ccache jobs ggml-org/llama.cpp

Local LLMs

wire 2026-08-21

DeepSeek V4 fuses shared experts, as vLLM ships a security guard

metal : dequantize quantized KV to F16 before flash attention (#27390) ggml-org/llama.cpp

Local LLMs

wire 2026-08-03

DEEPSEEK V4 INFERENCE GETS 50% SPEEDUP; LLAMA.CPP AND VLLM BOTH SHIPPING OPTIMIZED PATHS

metal: implement DeepSeek V4 hyper-connections ggml-org/llama.cpp