github llama.cpp · 5d ago · inference

llama.cpp b11206 adds Hexagon backend sampler support

from English

The llama.cpp project released version b11206, which introduces support for the Hexagon backend sampler. This update includes several changes to the sampling pipeline and operations on the Hexagon NPU.

Added STEP and SUM operations to the hex-sampler.
Updated CPY to support sampling cases.
Added chunking support in hex-binary to handle large logits.
Implemented a basic version of ARGMAX for hex-argmax.
Fixed indexing issues for dim 1 broadcasts across dim 2 slices.
Disabled the autovectorizer to use explicit hints for critical loops.

The release provides binaries for macOS, Linux, Windows, Android, and openEuler across various hardware backends including CPU, GPU, and NPU.

Importance 1/3 Trust 1/3 llama.cpp Inference efficiency Local inference

Read original

media Hugging Face Forums · just now · 1 view Live

AiiStream Q3.6 enables running Qwen3.6-35B-A3B on 8-16 GB Macs

The author has released AiiStream Q3.6, an open-source technique that allows the Qwen3.6-35B-A3B model to run on Apple Silicon devices with only 8 to 16 GB of RAM. By keeping routed experts on SSD and using early loading predictions, the method reduces MLX memory usage to approximately 1.7 GB while maintaining byte-identical outputs to the standard mlx_lm implementation.

github llama.cpp · 22h ago · 1 view

llama.cpp b11307 preserves batch order for speculative decoding

The llama.cpp project released build b11307, which fixes layer input ordering to preserve the original batch sequence during speculative decoding. This change ensures that token order is correctly maintained for unmasked NextN embeddings and compatible with tensor splits.

github llama.cpp · 1d ago · 1 view

llama.cpp b11301 fixes integer overflow in ggml/gguf

The llama.cpp project has released build b11301, which includes a fix for an integer overflow issue within the ggml and gguf components. This update addresses validation logic to prevent potential errors when handling zero-element tensors.

github llama.cpp · 1d ago · 3 views

llama.cpp b11302 fixes ThreadSanitizer data race in sparse indexer

The llama.cpp project released build b11302, which addresses a critical concurrency issue identified by ThreadSanitizer in the CI pipeline. The update resolves a data race within the sparse attention mechanism where multiple CPU threads were incorrectly writing to the same memory elements.

github llama.cpp · 1d ago · 2 views

llama.cpp b11298 adds dflash support to convert and feature extraction

The llama.cpp project has released build b11298, which introduces support for the dflash format. This update enables both conversion of models to this format and subsequent feature extraction capabilities.