mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-05-01 20:01:42 +00:00
Add GitHub data: filename sanitization (#640)
This commit is contained in:
14
github-data/pull_requests/109 - Bitnet CUDA improvements.md
Normal file
14
github-data/pull_requests/109 - Bitnet CUDA improvements.md
Normal file
@@ -0,0 +1,14 @@
|
||||
### 🔀 [#109](https://github.com/ikawrakow/ik_llama.cpp/pull/109) - Bitnet CUDA improvements
|
||||
|
||||
| **Author** | `ikawrakow` |
|
||||
| :--- | :--- |
|
||||
| **State** | ❌ **Closed** |
|
||||
| **Created** | 2024-10-26 |
|
||||
| **Updated** | 2024-10-26 |
|
||||
|
||||
---
|
||||
|
||||
#### Description
|
||||
|
||||
`IQ1_BN` TG-128 on RTX-4080 goes to 340 t/s up from 318 t/s.
|
||||
On the front page the performance listed for `IQ1_BN` on CUDA is 301 t/s, so a pretty nice improvement since then.
|
||||
Reference in New Issue
Block a user