We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 1e97e68 commit 4513b24Copy full SHA for 4513b24
README.md
@@ -24,7 +24,7 @@ This fork is specifically optimized for AMD GFX906 architecture (MI50, MI60, Veg
24
### Performance comparison -- lama bench
25
- did not use the -d because long prompt processing make gpu to reach 80C and throttle, making the comparison difficult
26
- all models tested with:
27
-| ---------- | --- | ------- | ------- | ------ | ------ | -- |
+
28
| backend | ngl | threads | n_batch | type_k | type_v | fa |
29
| ROCm | 99 | 12 | 1024 | q8_0 | q8_0 | 1 |
30
| ---------- | --- | ------- | ------- | ------ | ------ | -- |
0 commit comments