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, 00:45 UTC
[Hardware][Gaudi][Doc] Add missing step in setup instructions (#12382)
Mohit Deopujari committed
Jan 24, 2025 at 01:43 UTC
9a0f3bdbe530f4d90e27cf9c6f5cc506e2b44c03
1 file changed
+2
docs/source/getting_started/installation/ai_accelerator/hpu-gaudi.inc.md
+2
@@ -59,6 +59,7 @@ To build and install vLLM from source, run:
59
```console
60
git clone https://github.com/vllm-project/vllm.git
61
cd vllm
62
+pip install -r requirements-hpu.txt
63
python setup.py develop
64
```
65
@@ -68,6 +69,7 @@ Currently, the latest features and performance optimizations are developed in Ga
69
git clone https://github.com/HabanaAI/vllm-fork.git
70
cd vllm-fork
71
git checkout habana_main
72
+pip install -r requirements-hpu.txt
73
python setup.py develop
74
```
75