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, 04:45 UTC
[Doc] Update V1 user guide for embedding models (#19842)
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
22quinn committed
Jun 19, 2025 at 02:43 UTC
6f68c492204946b7de33d91fcd7c5439ef4aa9a3
1 file changed
+6
-6
docs/usage/v1_guide.md
+6
-6
@@ -39,9 +39,9 @@ This living user guide outlines a few known **important changes and limitations*
39
For each item, our progress towards V1 support falls into one of the following states:
40
41
- **🚀 Optimized**: Nearly fully optimized, with no further work currently planned.
42
-- **🟢 Functional**: Fully operational, with ongoing optimizations.
43
-- **🚧 WIP**: Under active development.
44
-- **🟡 Planned**: Scheduled for future implementation (some may have open PRs/RFCs).
42
+- **🟢 Functional**: Fully operational, with ongoing optimizations.
43
+- **🚧 WIP**: Under active development.
44
+- **🟡 Planned**: Scheduled for future implementation (some may have open PRs/RFCs).
45
- **🟠 Delayed**: Temporarily dropped in V1 but planned to be re-introduced later.
46
- **🔴 Deprecated**: Not planned for V1 unless there is strong demand.
47
@@ -70,7 +70,7 @@ For each item, our progress towards V1 support falls into one of the following s
70
|-----------------------------|------------------------------------------------------------------------------------|
71
| **Decoder-only Models** | <nobr>🚀 Optimized</nobr> |
72
| **Encoder-Decoder Models** | <nobr>🟠 Delayed</nobr> |
73
-| **Embedding Models** | <nobr>🚧 WIP ([PR #16188](https://github.com/vllm-project/vllm/pull/16188))</nobr> |
73
+| **Embedding Models** | <nobr>🟢 Functional</nobr> |
74
| **Mamba Models** | <nobr>🚧 WIP ([PR #19327](https://github.com/vllm-project/vllm/pull/19327))</nobr> |
75
| **Multimodal Models** | <nobr>🟢 Functional</nobr> |
76
@@ -80,11 +80,11 @@ vLLM V1 currently excludes model architectures with the `SupportsV0Only` protoco
80
81
This corresponds to the V1 column in our [list of supported models][supported-models].
82
83
-See below for the status of models that are still not yet supported in V1.
83
+See below for the status of models that are not yet supported or have more features planned in V1.
84
85
#### Embedding Models
86
87
-The initial support will be provided by [PR #16188](https://github.com/vllm-project/vllm/pull/16188).
87
+The initial basic support is now functional.
88
89
Later, we will consider using [hidden states processor](https://github.com/vllm-project/vllm/issues/12249),
90
which is based on [global logits processor](https://github.com/vllm-project/vllm/pull/13360)