Developing story · 2 episodes · 16 Sept to 16 Sept
Llama.cpp Advances with Qwen Graph and Mimir Support
The open-source Llama.cpp project has been progressively enhancing its capabilities by merging high‑performance operations into the Qwen4exp graph and adding HRM‑Text support for the DFM Mimir 1B model. With the latest b11003 release, the engine now runs the Mimir model efficiently, marking a significant step toward broader AI model compatibility.
-
llama.cpp b11003 adds HRM-Text support for DFM Mimir 1B model
The llama.cpp project released version b11003, introducing support for the HRM‑Text architecture used by the DFM Mimir 1B model. The new implementation runs two transformer stacks—low and high—in an…
1 source primary source -
ggml-org Merges hc Ops into qwen4exp Graph in llama.cpp
A recent pull request (28901) in the open‑source llama.cpp repository has added new high‑capacity (hc) operations to the qwen4exp graph, targeting both CPU and CUDA backends. The changes fuse a…
1 source primary source
Who and what
ggml-orgdeepseekHugging Faceqwen4expDFM Mimir 1BHRM-Textfeal87pwilkinggerganovSigbjørn SkjæretClaude Sonnet