A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 20:45 UTC
Update README.md (#6847)
Gurpreet Singh Dhami committed
Jul 26, 2024 at 20:26 UTC
b5f49ee55beac7bb314fd8880bdb718ed117dacb
1 file changed
+1
-1
examples/fp8/quantizer/README.md
+1
-1
@@ -16,7 +16,7 @@
16
#### Run on H100 system for speed if FP8; number of GPUs depends on the model size
17
18
#### Example: quantize Llama2-7b model from HF to FP8 with FP8 KV Cache:
19
-`python quantize.py --model_dir ./ll2-7b --dtype float16 --qformat fp8 --kv_cache_dtype fp8 --output_dir ./ll2_7b_fp8 --calib_size 512 --tp_size 1`
19
+`python quantize.py --model-dir ./ll2-7b --dtype float16 --qformat fp8 --kv-cache-dtype fp8 --output-dir ./ll2_7b_fp8 --calib-size 512 --tp-size 1`
20
21
Outputs: model structure, quantized model & parameters (with scaling factors) are in JSON and Safetensors (npz is generated only for the reference)
22
```