RYDE-WORK/ktransformers
1
0
Fork 0
mirror of https://github.com/RYDE-WORK/ktransformers.git synced 2026-01-19 12:43:16 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #144 from kvcache-ai/KMSorSMS-patch-1

Browse Source 
Km sor sms patch 1
This commit is contained in:
ZiWei Yuan 2025-02-11 22:07:37 +08:00 committed by GitHub
commit a2fc2a8658
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -140,7 +140,7 @@ Some preparation:
pip install ktransformers --no-build-isolation
```
for windows we prepare a pre compiled whl package in [ktransformers-0.1.1+cu125torch24avx2-cp311-cp311-win_amd64.whl](https://github.com/kvcache-ai/ktransformers/releases/download/v0.1.1/ktransformers-0.1.1+cu125torch24avx2-cp311-cp311-win_amd64.whl), which require cuda-12.5, torch-2.4, python-3.11, more pre compiled package are being produced.
for windows we prepare a pre compiled whl package on [ktransformers-0.2.0+cu125torch24avx2-cp312-cp312-win_amd64.whl](https://github.com/kvcache-ai/ktransformers/releases/download/v0.2.0/ktransformers-0.2.0+cu125torch24avx2-cp312-cp312-win_amd64.whl), which require cuda-12.5, torch-2.4, python-3.11, more pre compiled package are being produced.
3. Or you can download source code and compile:
@ -213,6 +213,8 @@ It features the following arguments:
| Model Name | Model Size | VRAM | Minimum DRAM | Recommended DRAM |
| ------------------------------ | ---------- | ----- | --------------- | ----------------- |
| DeepSeek-R1-q4_k_m | 377G | 14G | 382G | 512G |
| DeepSeek-V3-q4_k_m | 377G | 14G | 382G | 512G |
| DeepSeek-V2-q4_k_m | 133G | 11G | 136G | 192G |
| DeepSeek-V2.5-q4_k_m | 133G | 11G | 136G | 192G |
| DeepSeek-V2.5-IQ4_XS | 117G | 10G | 107G | 128G |