mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-03-17 16:44:07 +00:00
Updated Feature matrix (markdown)
@@ -3,7 +3,7 @@
|
||||
| **K-quants** | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ 🐢⁵ | ✅ 🐢⁵ | 🚫 |
|
||||
| **I-quants** | ✅ 🐢⁴ | ✅ 🐢⁴ | ✅ 🐢⁴ | ✅ | ✅ | Partial¹ | 🚫 | 🚫 | 🚫 |
|
||||
| **Multi-GPU** | N/A | N/A | N/A | ✅ | ❓ | 🚫 | ❓ | ✅ | ❓ |
|
||||
| **K cache quants** | ✅ | ❓ | ❓ | ✅ 🐢³ | Partial⁶ 🐢³ | ❓ | ✅ | 🚫 | 🚫 |
|
||||
| **K cache quants** | ✅ | ❓ | ✅ | ✅ 🐢³ | Partial⁶ 🐢³ | ❓ | ✅ | 🚫 | 🚫 |
|
||||
| **MoE architecture** | ✅ | ❓ | ✅ | ✅ | ✅ | ❓ | Partial² | 🚫 | 🚫 |
|
||||
|
||||
* ✅: feature works
|
||||
|
||||
Reference in New Issue
Block a user