Skip to content

[Doc] Update V1 User Guide for Hardware and Models #19474

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Jun 11, 2025
Merged

[Doc] Update V1 User Guide for Hardware and Models #19474

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
87d5797
[Doc] Update V1 Guide for hardware and models
DarkLight1337 Jun 11, 2025
b0dc14f
Change the heading level
DarkLight1337 Jun 11, 2025
7e9f46a
More reorganization
DarkLight1337 Jun 11, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
148 changes: 81 additions & 67 deletions docs/usage/v1_guide.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
# vLLM V1

**We have started the process of deprecating V0. Please read [RFC #18571](https://github.com/vllm-project/vllm/issues/18571) for more details.**
!!! important

We have started the process of deprecating V0. Please read [RFC #18571](https://github.com/vllm-project/vllm/issues/18571) for more details.

V1 is now enabled by default for all supported use cases, and we will gradually enable it for every use case we plan to support. Please share any feedback on [GitHub](https://github.com/vllm-project/vllm) or in the [vLLM Slack](https://inviter.co/vllm-slack).

Expand Down Expand Up @@ -32,53 +34,92 @@ Upgrade to vLLM’s Core Architecture](https://blog.vllm.ai/2025/01/27/v1-alpha-

This living user guide outlines a few known **important changes and limitations** introduced by vLLM V1. The team has been working actively to bring V1 as the default engine, therefore this guide will be updated constantly as more features get supported on vLLM V1.

### Supports Overview
#### Hardware
## Current Status

For each item, our progress towards V1 support falls into one of the following states:

- **🚀 Optimized**: Nearly fully optimized, with no further work currently planned.
- **🟢 Functional**: Fully operational, with ongoing optimizations.
- **🚧 WIP**: Under active development.
- **🟡 Planned**: Scheduled for future implementation (some may have open PRs/RFCs).
- **🟠 Delayed**: Temporarily dropped in V1 but planned to be re-introduced later.
- **🔴 Deprecated**: Not planned for V1 unless there is strong demand.

### Hardware

| Hardware | Status |
|------------|------------------------------------|
| **NVIDIA** | <nobr>🚀</nobr> |
| **AMD** | <nobr>🟢</nobr> |
| **TPU** | <nobr>🟢</nobr> |
| **CPU** | <nobr>🟢 (x86) 🟡 (MacOS) </nobr> |

!!! note

More hardware platforms may be supported via plugins, e.g.:

- [vllm-ascend](https://github.com/vllm-project/vllm-ascend)
- [vllm-spyre](https://github.com/vllm-project/vllm-spyre)
- [vllm-openvino](https://github.com/vllm-project/vllm-openvino)

Please check their corresponding repositories for more details.

### Models

| Model Type | Status |
|-----------------|-----------------------------------------------------------------------------------|
| **Decoder-only Models** | <nobr>🚀 Optimized</nobr> |
| **Encoder-Decoder Models** | <nobr>🟠 Delayed</nobr> |
| **Embedding Models** | <nobr>🚧 WIP ([PR #16188](https://github.com/vllm-project/vllm/pull/16188))</nobr> |
| **Mamba Models** | <nobr>🚧 WIP ([PR #19327](https://github.com/vllm-project/vllm/pull/19327))</nobr> |
| **Multimodal Models** | <nobr>🟢 Functional</nobr> |

| Hardware | Status |
|----------|------------------------------------------|
| **NVIDIA** | <nobr>🚀 Natively Supported</nobr> |
| **AMD** | <nobr>🚧 WIP</nobr> |
| **TPU** | <nobr>🚧 WIP</nobr> |
| **CPU** | <nobr>🚧 WIP</nobr> |
vLLM V1 currently excludes model architectures with the `SupportsV0Only` protocol,
and the majority fall into the following categories:

#### Feature / Model
**Embedding Models**
The initial support will be provided by [PR #16188](https://github.com/vllm-project/vllm/pull/16188).

| Feature / Model | Status |
Later, we will consider using [hidden states processor](https://github.com/vllm-project/vllm/issues/12249),
which is based on [global logits processor](https://github.com/vllm-project/vllm/pull/13360)
to enable simultaneous generation and embedding using the same engine instance in V1.

**Mamba Models**
Models using selective state-space mechanisms instead of standard transformer attention (e.g., `MambaForCausalLM`, `JambaForCausalLM`)
will be supported via [PR #19327](https://github.com/vllm-project/vllm/pull/19327).

**Encoder-Decoder Models**
vLLM V1 is currently optimized for decoder-only transformers.
Models requiring cross-attention between separate encoder and decoder are not yet supported (e.g., `BartForConditionalGeneration`, `MllamaForConditionalGeneration`).

For a complete list of supported models, see the [list of supported models](https://docs.vllm.ai/en/latest/models/supported_models.html).

### Features

| Feature | Status |
|-----------------|-----------------------------------------------------------------------------------|
| **Prefix Caching** | <nobr>🚀 Optimized</nobr> |
| **Chunked Prefill** | <nobr>🚀 Optimized</nobr> |
| **Prefix Caching** | <nobr>🚀 Optimized</nobr> |
| **Chunked Prefill** | <nobr>🚀 Optimized</nobr> |
| **LoRA** | <nobr>🚀 Optimized</nobr> |
| **Logprobs Calculation** | <nobr>🟢 Functional</nobr> |
| **Multimodal Models** | <nobr>🟢 Functional</nobr> |
| **FP8 KV Cache** | <nobr>🟢 Functional on Hopper devices ([PR #15191](https://github.com/vllm-project/vllm/pull/15191))</nobr>|
| **Spec Decode** | <nobr>🚧 WIP ([PR #13933](https://github.com/vllm-project/vllm/pull/13933))</nobr>|
| **Prompt Logprobs with Prefix Caching** | <nobr>🟡 Planned ([RFC #13414](https://github.com/vllm-project/vllm/issues/13414))</nobr>|
| **Structured Output Alternative Backends** | <nobr>🟢 Functional</nobr> |
| **Embedding Models** | <nobr>🚧 WIP ([PR #16188](https://github.com/vllm-project/vllm/pull/16188))</nobr> |
| **Mamba Models** | <nobr>🟡 Planned</nobr> |
| **Encoder-Decoder Models** | <nobr>🟠 Delayed</nobr> |
| **Request-level Structured Output Backend** | <nobr>🔴 Deprecated</nobr> |
| **best_of** | <nobr>🔴 Deprecated ([RFC #13361](https://github.com/vllm-project/vllm/issues/13361))</nobr>|
| **Per-Request Logits Processors** | <nobr>🔴 Deprecated ([RFC #13360](https://github.com/vllm-project/vllm/pull/13360))</nobr> |
| **GPU <> CPU KV Cache Swapping** | <nobr>🔴 Deprecated</nobr> |

- **🚀 Optimized**: Nearly fully optimized, with no further work currently planned.
- **🟢 Functional**: Fully operational, with ongoing optimizations.
- **🚧 WIP**: Under active development.
- **🟡 Planned**: Scheduled for future implementation (some may have open PRs/RFCs).
- **🟠 Delayed**: Temporarily dropped in V1 but planned to be re-introduced later.
- **🔴 Deprecated**: Not planned for V1 unless there is strong demand.
!!! note

**Note**: vLLM V1’s unified scheduler treats both prompt and output tokens the same
way by using a simple dictionary (e.g., `{request_id: num_tokens}`) to dynamically
allocate a fixed token budget per request, enabling features like chunked prefills,
prefix caching, and speculative decoding without a strict separation between prefill
and decode phases.
vLLM V1’s unified scheduler treats both prompt and output tokens the same
way by using a simple dictionary (e.g., `{request_id: num_tokens}`) to dynamically
allocate a fixed token budget per request, enabling features like chunked prefills,
prefix caching, and speculative decoding without a strict separation between prefill
and decode phases.

### Semantic Changes and Deprecated Features

#### Logprobs
#### Semantic Changes to Logprobs

vLLM V1 supports logprobs and prompt logprobs. However, there are some important semantic
differences compared to V0:
Expand All @@ -96,6 +137,14 @@ Support for logprobs with post-sampling adjustments is in progress and will be a

Currently prompt logprobs are only supported when prefix caching is turned off via `--no-enable-prefix-caching`. In a future release, prompt logprobs will be compatible with prefix caching, but a recomputation will be triggered to recover the full prompt logprobs even upon a prefix cache hit. See details in [RFC #13414](https://github.com/vllm-project/vllm/issues/13414).

#### WIP Features

These features are already supported in vLLM V1, but their optimization is still
in progress.

- **Spec Decode**: Currently, only ngram-based spec decode is supported in V1. There
will be follow-up work to support other types of spec decode (e.g., see [PR #13933](https://github.com/vllm-project/vllm/pull/13933)). We will prioritize the support for Eagle, MTP compared to draft model based spec decode.

#### Deprecated Features

As part of the major architectural rework in vLLM V1, several legacy features have been deprecated.
Expand All @@ -115,39 +164,4 @@ to handle request preemptions.

**Structured Output features**

- **Request-level Structured Output Backend**: Deprecated, alternative backends
(outlines, guidance) with fallbacks is WIP.
### Feature & Model Support in Progress

Although we have re-implemented and partially optimized many features and models from V0 in vLLM V1, optimization work is still ongoing for some, and others remain unsupported.

#### Features to Be Optimized

These features are already supported in vLLM V1, but their optimization is still
in progress.

- **Spec Decode**: Currently, only ngram-based spec decode is supported in V1. There
will be follow-up work to support other types of spec decode (e.g., see [PR #13933](https://github.com/vllm-project/vllm/pull/13933)). We will prioritize the support for Eagle, MTP compared to draft model based spec decode.

- **Multimodal Models**: V1 is almost fully compatible with V0 except that interleaved modality input is not supported yet.
See [here](https://github.com/orgs/vllm-project/projects/8) for the status of upcoming features and optimizations.

#### Models to Be Supported

vLLM V1 currently excludes model architectures with the `SupportsV0Only` protocol,
and the majority fall into the following categories. V1 support for these models will be added eventually.

**Embedding Models**
The initial support will be provided by [PR #16188](https://github.com/vllm-project/vllm/pull/16188).

Later, we will consider using [hidden states processor](https://github.com/vllm-project/vllm/issues/12249), which is based on [global logits processor](https://github.com/vllm-project/vllm/pull/13360) to enable simultaneous generation and embedding using the same engine instance in V1.

**Mamba Models**
Models using selective state-space mechanisms (instead of standard transformer attention)
are not yet supported (e.g., `MambaForCausalLM`, `JambaForCausalLM`).

**Encoder-Decoder Models**
vLLM V1 is currently optimized for decoder-only transformers. Models requiring
cross-attention between separate encoder and decoder are not yet supported (e.g., `BartForConditionalGeneration`, `MllamaForConditionalGeneration`).

For a complete list of supported models, see the [list of supported models](https://docs.vllm.ai/en/latest/models/supported_models.html).
- **Request-level Structured Output Backend**: Deprecated, alternative backends (outlines, guidance) with fallbacks is supported now.
3 changes: 2 additions & 1 deletion vllm/engine/arg_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1440,7 +1440,8 @@ def _is_v1_supported_oracle(self, model_config: ModelConfig) -> bool:
_raise_or_fallback(feature_name=name, recommend_to_remove=False)
return False

# Non-[CUDA, TPU] may be supported on V1, but off by default for now.
# Non-[CUDA, TPU, x86 CPU] may be supported on V1,
# but off by default for now.
v0_hardware = not any(
(current_platform.is_cuda_alike(), current_platform.is_tpu(),
(current_platform.is_cpu()
Expand Down