@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 001a9c7b0d
Fork 0

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 15, 19:45 UTC

[Doc] Update PaliGemma note to a warning (#14565)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

Cyrus Leung committed Mar 10, 2025 at 23:02 UTC 001a9c7b0d513bbe018c5eb8eea2c4e678e52787
1 file changed +7 -5
docs/source/models/supported_models.md
+7 -5
@@ -847,7 +847,7 @@ See [this page](#generative-models) for more information on how to use generativ
847 * ✅︎
848 * ✅︎
849 - * `PaliGemmaForConditionalGeneration`
850 - * PaliGemma (see note), PaliGemma 2 (see note)
850 + * PaliGemma ⚠️, PaliGemma 2 ⚠️
851 * T + I<sup>E</sup>
852 * `google/paligemma-3b-pt-224`, `google/paligemma-3b-mix-224`, `google/paligemma2-3b-ft-docci-448`, etc.
853 *
@@ -917,6 +917,12 @@ See [this page](#generative-models) for more information on how to use generativ
917 <sup>E</sup> Pre-computed embeddings can be inputted for this modality.
918 <sup>+</sup> Multiple items can be inputted per text prompt for this modality.
919
920 +:::{warning}
921 +vLLM does not currently support PrefixLM attention mask, so our PaliGemma implementation uses regular causal attention, which causes the model output to be unstable.
922 +
923 +We may deprecate this model series in a future release.
924 +:::
925 +
926 :::{note}
927 `h2oai/h2ovl-mississippi-2b` will be available in V1 once we support backends other than FlashAttention.
928 :::
@@ -930,10 +936,6 @@ The official `openbmb/MiniCPM-V-2` doesn't work yet, so we need to use a fork (`
936 For more details, please see: <gh-pr:4087#issuecomment-2250397630>
937 :::
938
933 -:::{note}
934 -Currently the PaliGemma model series is implemented without PrefixLM attention mask. This model series may be deprecated in a future release.
935 -:::
936 -
939 :::{note}
940 To use Qwen2.5-VL series models, you have to install Hugging Face Transformers library from source via `pip install git+https://github.com/huggingface/transformers`.
941 :::