#memory-optimization

[ follow ]
#ai #__slots__ #attribute-lookup #data-compression #turboquant #quantization #intel-core-ultra-200s-plus
#ai
fromTheregister
2 days ago
Data science

TurboQuant is a big deal, but it won't end the memory crunch

TurboQuant is an AI data compression technology that reduces memory usage for KV caches but may not significantly alleviate memory shortages.
fromHackernoon
1 year ago
Artificial intelligence

Time Space Breakthrough, Ancient Memory Systems & An I-Ching Inspired Hyper-Stack Scheduler | HackerNoon

Memory is the key limitation in AI and computing, with RAM often dictating the achievable scale.
Data science
fromTheregister
2 days ago

TurboQuant is a big deal, but it won't end the memory crunch

TurboQuant is an AI data compression technology that reduces memory usage for KV caches but may not significantly alleviate memory shortages.
fromHackernoon
1 year ago
Artificial intelligence

Time Space Breakthrough, Ancient Memory Systems & An I-Ching Inspired Hyper-Stack Scheduler | HackerNoon

more#ai
Mobile UX
fromGSMArena.com
3 weeks ago

Intel unveils $200 Core Ultra 5 250K Plus and $300 Core Ultra 7 270K Plus CPUs

Intel's Core Ultra 200S Plus series delivers 15% faster gaming performance with additional E cores, lower memory latency, and optimized pricing for current motherboards.
Python
fromPyImageSearch
3 weeks ago

DeepSeek-V3 Model: Theory, Config, and Rotary Positional Embeddings - PyImageSearch

DeepSeek-V3 introduces revolutionary architectural innovations including Multihead Latent Attention that reduces KV cache memory by 75% while maintaining model quality, addressing critical challenges in inference efficiency, training cost, and long-range dependency capture.
Software development
fromTheregister
2 months ago

Brave refurbishes Rust adblock engine for memory gain

Brave's reworked Rust adblock engine reduces memory consumption by about 75%, saving roughly 45 MB per platform and improving battery life and multitasking.
Python
fromPythonmorsels
4 months ago

__slots__ for optimizing classes

__slots__ replaces per-instance __dict__ with fixed named slots, preventing dynamic attribute assignment and reducing memory and attribute lookup overhead.
Python
fromPythonmorsels
4 months ago

__slots__ for optimizing classes

Using __slots__ removes the per-instance __dict__, restricts allowed attributes, and improves memory usage and attribute access speed.
Python
fromTechBeamers
6 months ago

Python Memory Tricks to Boost Performance

Use Python 3.13's mimalloc and memory-aware coding techniques to reduce memory usage and prevent MemoryError and leaks.
Software development
fromInfoQ
8 months ago

Grafana Tempo 2.8 Released: Major TraceQL Enhancements and Memory Optimizations

Tempo 2.8 significantly enhances memory efficiency and introduces new features to TraceQL.
[ Load more ]