Skip to content

GitLab

"git@developer.sourcefind.cn:OpenDAS/mmcv.git" did not exist on "2a82b52b8d4a0d75d133ffdabf894ef4af39fb3d"
Unverified Commit a2fc2a86 authored by ZiWei Yuan's avatar ZiWei Yuan Committed by GitHub
Browse files

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

Km sor sms patch 1
parents e34df760 cfbdb665
Hide whitespace changes
Inline Side-by-side
Showing with 3 additions and 1 deletion
README.md
View file @ a2fc2a86
...@@ -140,7 +140,7 @@ Some preparation: ...@@ -140,7 +140,7 @@ Some preparation:
pip install ktransformers --no-build-isolation 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: 3. Or you can download source code and compile:
...@@ -213,6 +213,8 @@ It features the following arguments: ...@@ -213,6 +213,8 @@ It features the following arguments:
| Model Name | Model Size | VRAM | Minimum DRAM | Recommended DRAM | | 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-q4_k_m | 133G | 11G | 136G | 192G |
| DeepSeek-V2.5-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 | | DeepSeek-V2.5-IQ4_XS | 117G | 10G | 107G | 128G |
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment