ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-05-04 13:21:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add GitHub data: filename sanitization (#640)

Browse Source
This commit is contained in:
Thomas
2025-07-23 13:31:53 +02:00
committed by GitHub
parent 3600d82e98
commit eaa2510a28
626 changed files with 0 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
github-data/issues/196 - Refactor_ remove usage of Q8_1 for activation quantization.md Normal file
View File

@@ -0,0 +1,22 @@
### 📝 [#196](https://github.com/ikawrakow/ik_llama.cpp/issues/196) - Refactor: remove usage of Q8_1 for activation quantization
| **Author** | `ikawrakow` |
| :--- | :--- |
| **State** | ❌ **Closed** |
| **Created** | 2025-02-09 |
| **Updated** | 2025-03-27 |
---
#### Description
### Background Description
Some models can produce activations that are beyond the range of `fp16`. In that scenario, usage of `Q8_1` to quantize the activations can be futile, see discussion in #194.
Hence, it would be prudent to change all quantization types using `Q8_1` for matrix multiplications to use something else.
Alternatively, one may replace the `fp16` block scale and block sum in `Q8_1` with `bf16`.
### Possible Refactor Approaches
_No response_