mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-05-04 13:21:37 +00:00
Add GitHub data: filename sanitization (#640)
This commit is contained in:
13
github-data/pull_requests/50 - AVX2 Flash Attention 2.md
Normal file
13
github-data/pull_requests/50 - AVX2 Flash Attention 2.md
Normal file
@@ -0,0 +1,13 @@
|
||||
### 🔀 [#50](https://github.com/ikawrakow/ik_llama.cpp/pull/50) - AVX2 Flash Attention 2
|
||||
|
||||
| **Author** | `ikawrakow` |
|
||||
| :--- | :--- |
|
||||
| **State** | ❌ **Closed** |
|
||||
| **Created** | 2024-09-11 |
|
||||
| **Updated** | 2024-09-11 |
|
||||
|
||||
---
|
||||
|
||||
#### Description
|
||||
|
||||
This PR adds the ability to use Q4_0, Q4_1 and Q8_0 for the kv-cache.
|
||||
Reference in New Issue
Block a user