7 Feature matrix

Romain D edited this page 2024-03-21 17:23:28 +00:00

	CPU (AVX2)	CPU (ARM NEON)	Metal	cuBLAS	rocBLAS	SYCL	CLBlast	Vulkan	Kompute
K-quants	✅	✅	✅	✅	✅	✅	✅ 🐢⁵	✅ 🐢⁵	🚫
I-quants	✅ 🐢⁴	✅ 🐢⁴	✅ 🐢⁴	✅	✅	Partial¹	🚫	🚫	🚫
Multi-GPU	N/A	N/A	N/A	✅	❓	🚫	❓	✅	❓
K cache quants	✅	❓	✅	✅ 🐢³	Partial⁶ 🐢³	❓	✅	🚫	🚫
MoE architecture	✅	❓	✅	✅	✅	❓	Partial²	🚫	🚫

• ✅: feature works
• 🚫: feature does not work
• ❓: unknown, please contribute if you can test it youself
• 🐢: feature is slow
• ¹: IQ3_S and IQ1_S, see #5886
• ²: Only with -ngl 0
• ³: Inference is 50% slower
• ⁴: Slower than K-quants of comparable size
• ⁵: Slower than cuBLAS/rocBLAS on similar cards
• ⁶: Only q8_0 and iq4_nl

Users Guide

Useful information for users that doesn't fit into Readme.

• Home
  • Install
  • ArchLinux
  • Nix
  • NixOS
  • Android Termux
  • Windows Msys2
  • Debian (Ubuntu)
  • Redhat
• Feature Matrix
• GGML Tips & Tricks
• Chat Templating
• Metadata Override
• HuggingFace Model Card Metadata Interoperability Consideration

Technical Details

These are information useful for Maintainers and Developers which does not fit into code comments

• Tensor Encoding Schemes
• Terminology
• PR And Issue Tickets Maintenance
• Dev Notes

Github Actions Main Branch Status

Click on a badge to jump to workflow. This is here as a useful general view of all the actions so that we may notice quicker if main branch automation is broken and where.

• 
• 
• 
• 
• 
• 
• 
• 
• 
• 
• 
• 
• 
• 
•