From b6f0e80d54f3a0ab50688e0c391258a206f677d5 Mon Sep 17 00:00:00 2001 From: Taikono-Himazin Date: Mon, 22 Apr 2024 23:37:13 +0900 Subject: [PATCH] Update text-generation.md (#2095) Signed-off-by: Taikono-Himazin --- docs/content/docs/features/text-generation.md | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/docs/content/docs/features/text-generation.md b/docs/content/docs/features/text-generation.md index c11894e7e409..3f3f0b56ef00 100644 --- a/docs/content/docs/features/text-generation.md +++ b/docs/content/docs/features/text-generation.md @@ -257,6 +257,10 @@ parameters: # swap_space: 2 # Uncomment to specify the maximum length of a sequence (including prompt and output) # max_model_len: 32768 +# Uncomment and specify the number of Tensor divisions. +# Allows you to partition and run large models. Performance gains are limited. +# https://github.com/vllm-project/vllm/issues/1435 +# tensor_parallel_size: 2 ``` The backend will automatically download the required files in order to run the model. @@ -356,4 +360,4 @@ template: completion: | {{.Input}} -``` \ No newline at end of file +```