sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-03-17 16:44:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Updated Feature matrix (markdown)

Eve
2026-03-16 22:05:04 +00:00
parent 7056c55479
commit d7d4aedd6b
1 changed files with 8 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
Feature-matrix.md

@@ -1,19 +1,17 @@
| | **CPU (AVX/AVX2)** | **CPU (ARM NEON)** | **Metal** | **CUDA** | **ROCm** | **SYCL** | **Vulkan** | **Kompute** |
|:-----------------------:|:--------------:|:------------------:|:---------:|:----------:|:----------------:|:----------:|:----------:|:-----------:|
| **K-quants** | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ 🐢⁵ | 🚫 |
| **I-quants** | ✅ 🐢⁴ | ✅ 🐢⁴ | ✅ 🐢⁴ | ✅ | ✅ | Partial¹ | ✅ 🐢⁴ | 🚫 |
| **Parallel Multi-GPU⁶** | N/A | N/A | N/A | ✅ | ✅ | Sequential only | Sequential only | ❓ |
| **K cache quants** | ✅ | ✅ | ✅ | ✅ | ✅ | ❓ | ✅ | 🚫 |
| **MoE architecture** | ✅ | ✅ | ✅ | ✅ | ✅ | ❓ | ✅ | 🚫 |
| **Flash Attention** | ✅ | ✅ | ✅ | ✅ | ✅ | ❓ | ✅ | 🚫 |
| | **CPU (AVX/AVX2)** | **CPU (ARM NEON)** | **Metal** | **CUDA** | **ROCm** | **SYCL** | **Vulkan** |
|:-----------------------:|:--------------:|:------------------:|:---------:|:----------:|:----------------:|:----------:|:----------:|
| **K-quants** | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ 🐢⁵ |
| **I-quants** | ✅ 🐢⁴ | ✅ 🐢⁴ | ✅ 🐢⁴ | ✅ | ✅ | Partial¹ | ✅ 🐢⁴ |
| **Parallel Multi-GPU⁶** | N/A | N/A | N/A | ✅ | ✅ | Sequential only | Sequential only |
| **K cache quants** | ✅ | ✅ | ✅ | ✅ | ✅ | ❓ | ✅ |
| **MoE architecture** | ✅ | ✅ | ✅ | ✅ | ✅ | ❓ | ✅ |
| **Flash Attention** | ✅ | ✅ | ✅ | ✅ | ✅ | ❓ | ✅ |
* ✅: feature works
* 🚫: feature does not work
* ❓: unknown, please contribute if you can test it yourself
* 🐢: 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: Generally the CUDA or ROCM backends are faster, though there are cases where Vulkan has faster text generation. See #10879 for benchmarks.
* ⁶: By default, all GPU backends can utilize multiple devices by running them sequentially. The CUDA code (which is also used for ROCm via HIP) also has code for running GPUs in parallel via `--split-mode row`. However, this is optimized relatively poorly and is only faster if the interconnect speed is fast vs. the speed of a single GPU.