저장한 도구도구 추천
FOXAI SEARCH

전체 검색

뉴스 기사 198

startup-projects

Show HN: Record, branch, and compare command runs in stdlib-only Python

Hi, this is a package I developed for keeping track of short toy-model development cycles and explaining what changed between runs.The core idea: commands run through the package, and their declared parameters (or injected parameters with --substitute) and outcomes go into a dependency-free ledger stored in the project. Because that ledger lives in the project directory, it has worked well for passing context between different agents. I’ve also found some use for it in CI work. Comments URL: https://news.ycombinator.com/item?id=50417782 Points: 3 # Comments: 0

번역 서비스가 일시 중지되어 원문을 표시합니다.
Hacker News Show HN
open-models

Your Experts Have Partners. There's HOPE for Keeping Them Together

HOPE, a second-order expert pruning method for Mixture-of-Experts (MoE) language models, accounts for pairwise expert interactions by optimizing a quadratic program based on an interaction matrix derived from calibration data. Unlike first-order methods that prune experts independently, HOPE preserves cooperative expert groups, leading to better performance—especially at high pruning rates like 50%. On benchmarks such as SWE-Bench Pro, HOPE outperforms state-of-the-art first-order methods like REAP by up to +6.1%, maintaining model quality while significantly reducing memory footprint. The method requires only a single calibration pass and efficient quadratic programming, with negligible overhead. It has been validated on Qwen3.5 and GLM-4.5 models, showing consistent improvements across diverse tasks and calibration sets.

번역 서비스가 일시 중지되어 원문을 표시합니다.
Hugging Face 官方博客
inference-systems

b12202

The llama.cpp v1.220.2 release introduces enhanced BF16 precision support across multiple components, aligning with reference implementations by moving specific operations like GLM4 family projections, MiMoVL vision matmuls, and Qwen3-TTS speaker encoder conv1d to BF16 where appropriate. Backends such as CUDA, Hexagon, OpenCL, WebGPU, and Vulkan now uniformly handle GGML_PREC_BF16 similarly to F32, while CPU, SpaceMIT, and ET backends extend flash attention support to BF16 with F32 accumulation. Flash attention tests now include BF16 cases, and the KQ multiplication in Llama is updated to request BF16 precision. A TODO remains in clip.cpp for future work.

번역 서비스가 일시 중지되어 원문을 표시합니다.
llama.cpp releases
inference-systems

b12208

The ggml library has been updated to make tied selections in the radix Top-K algorithm deterministic on CUDA and Metal backends by replacing atomic compaction loops with a deterministic scheme using simdgroup scans and coalesced memory accesses. This change ensures byte-identical outputs across runs, improves performance by 20-45% on M5 Ultra hardware, and enables deterministic testing for Metal and ROCm. Redundant CUDA kernel resets were removed, and Vulkan/Metal changes were reduced or skipped.

번역 서비스가 일시 중지되어 원문을 표시합니다.
llama.cpp releases