deployedbyai
Follow

The Deploy Log | Companies | Free, no signup

llama.cpp

Every row from llama.cpp in The Deploy Log: 13 rows, newest first, each linking the publisher's own page. The newest shipped are llama.cpp b12210 and llama.cpp b12146. The first is dated and the newest . By lane: Tools and products 13. They fall in 3 months. The tables below count them by lane, month and platform, and date them.

Rows by lane
LaneRows
Tools and products13
Rows by month
MonthRows
4
8
1
Dates
FigureValue
First row dated
Newest row dated
Median days between release days, publisher's dates only4
Platforms the rows name
PlatformRows
Hugging Face1
Rows by month, llama.cppSeptember 2026: 1 row; October 2026: 8 rows; November 2026: 4 rows.SepOctNov2026184
Each bar counts the rows listed for that month. Data as of .

Every new row from llama.cpp in your feed reader: RSS | JSON Feed

llama.cpp b12210

CPU support for SpacemiT IME2 MXFP4 dense repack.

llama.cpp | Tools and products | Published

SOURCE llama.cpp, llama.cpp b12210

llama.cpp b12146

Metal backend fuses DeepSeek-V4/V4.1 and GLM MoE routing, including scale-bias routing norm for DeepSeek-V4.1.

llama.cpp | Tools and products | Published

SOURCE llama.cpp, llama.cpp b12146

llama.cpp b12148

Vulkan RDNA3/4 large-tile split-K optimization in llama.cpp.

llama.cpp | Tools and products | Published

SOURCE llama.cpp, llama.cpp b12148

llama.cpp v0.9.0

Adds OCP FP8 E4M3 quantization, flash_attn_ext_rows, four new architectures, Chatterbox TTS, and Gemma 4 E2B/E4B prefill optimizations.

llama.cpp | Tools and products | Published

SOURCE llama.cpp, llama.cpp v0.9.0

llama.cpp b12021

Gemma 4 images are resized without letterbox padding in llama.cpp release b12021.

llama.cpp | Tools and products | Published

SOURCE llama.cpp, llama.cpp b12021

llama.cpp Soprano TTS support

llama.cpp b11850 adds Soprano-80M and Soprano-1.1-80M audio generation models with a Qwen3 backbone.

llama.cpp | Tools and products | Published

SOURCE llama.cpp, llama.cpp Soprano TTS support

llama.cpp HF Hub model discovery

llama.cpp b11714 adds UI to discover and download models from Hugging Face Hub.

llama.cpp | Tools and products | Published

SOURCE llama.cpp, llama.cpp HF Hub model discovery

Muse Spark Open in llama.cpp

llama.cpp b11671 adds Muse Spark Open model support for text, vision, and audio.

llama.cpp | Tools and products | Published

SOURCE llama.cpp, Muse Spark Open in llama.cpp

llama.cpp v0.7.0

llama.cpp v0.7.0 adds LiliCorr speculative decoding, MTP for GLM5-Next, and a GPU cache for MoE experts with up to ~2.2x decode speedup.

llama.cpp | Tools and products | Published

SOURCE llama.cpp, llama.cpp v0.7.0

llama.cpp b11551

llama.cpp release b11551 adds MiniCPM-V 4.7 model support.

llama.cpp | Tools and products | Published

SOURCE llama.cpp, llama.cpp b11551

llama.cpp K2 Horizon support

llama.cpp b11454 adds K2 Horizon dense and MoVA model support.

llama.cpp | Tools and products | Published

SOURCE llama.cpp, llama.cpp K2 Horizon support

llama.cpp v0.6.0

llama.cpp v0.6.0 adds GLM-5.3-Flash 320B, Clef, Qwen4Exp MTP, and a new /v1/systemone server API.

llama.cpp | Tools and products | Published

SOURCE llama.cpp, llama.cpp v0.6.0

llama.cpp v0.5.0

llama.cpp v0.5.0 adds HRM-Text support, MiMo-V2.6 and HunyuanOCR conversion, and multi-address HTTP binding.

llama.cpp | Tools and products | Published

SOURCE llama.cpp, llama.cpp v0.5.0

llama.cpp in The Deploy Log For llama.cpp's own page or README, this badge links here: <a href="https://deployedbyai.com/log/company/5b11e1c65bdb/llama-cpp/?k=badge"><img src="https://deployedbyai.com/log/company/5b11e1c65bdb/badge.svg" alt="llama.cpp in The Deploy Log" width="251" height="20"></a>

One line every time AI actually ships, around the clock, free on Threads and Bluesky. Every one is in The Deploy Log with its source.

The Saturday edition is the week in one, free to read on the site, and by email if you want it: get it by email.