vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-15 09:39:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #1219 from kvcache-ai/Atream-patch-4

Browse source 
Update AMX.md
This commit is contained in:
Atream 2025-04-28 21:04:12 -06:00 • committed by GitHub
commit b703cc9c3d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
doc/en/AMX.md
View file

@ -20,9 +20,9 @@ Here is the Qwen3MoE startup command:
``` python
# llamafile backend
python ktransformers/server/main.py --architectures Qwen3MoeForCausalLM --model_path <model_dir> --gguf_path <gguf_dir> --optimize_config_path ktransformers/optimize/optimize_rules/Qwen3Moe-serve.yaml
python ktransformers/server/main.py --architectures Qwen3MoeForCausalLM --model_path <model_dir> --gguf_path <gguf_dir> --optimize_config_path ktransformers/optimize/optimize_rules/Qwen3Moe-serve.yaml --backend_type balance_serve
# AMX backend
python ktransformers/server/main.py --architectures Qwen3MoeForCausalLM --model_path <model_dir> --gguf_path <gguf_dir> --optimize_config_path ktransformers/optimize/optimize_rules/Qwen3Moe-serve-amx.yaml
python ktransformers/server/main.py --architectures Qwen3MoeForCausalLM --model_path <model_dir> --gguf_path <gguf_dir> --optimize_config_path ktransformers/optimize/optimize_rules/Qwen3Moe-serve-amx.yaml --backend_type balance_serve
```
**Note: At present, Qwen3MoE running with AMX can only read BF16 GGUF; support for loading from safetensor will be added later.**