media Hugging Face Forums · 3d ago · open_models

TheImmortalPython releases pklm-sandbox for local token masking

from English

TheImmortalPython has released pklm-sandbox, a lightweight open-source tool designed for developers experimenting with custom generation constraints in Hugging Face transformers.

It provides a straightforward sandbox to test custom token-masking pipelines and zero-drift linguistic containment using the LogitsProcessor architecture.
Installation is available via pip from the GitHub repository.
The processor allows users to block specific token IDs directly within the standard generate() pipeline.

The project aims to give developers a clean starting point for implementing custom token control locally.

Importance 1/3 Trust 1/3 Hugging Face Forums 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 · 10h ago · 1 view

llama.cpp b11320 adds LLM-jp-4.1 Harmony dialect handler

The llama.cpp project released build b11320, which includes a new dialect handler for the LLM-jp-4.1 model.

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.