biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V0 deprecation] Remove more V0 references (#29088)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2025-11-21 19:56:59 +08:00
committed by GitHub
parent b34129bf8e
commit aab0102a26
15 changed files with 31 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/contributing/model/basic.md
View File

@@ -133,8 +133,6 @@ We consider 3 different scenarios:
For case (1), we recommend looking at the implementation of [`MambaForCausalLM`](../../../vllm/model_executor/models/mamba.py) (for Mamba-1) or [`Mamba2ForCausalLM`](../../../vllm/model_executor/models/mamba2.py) (for Mamba-2) as a reference.
The model should inherit protocol `IsAttentionFree` and also implement class methods `get_mamba_state_dtype_from_config` and `get_mamba_state_shape_from_config` to calculate the state shapes and data types from the config.
For the mamba layers themselves, please use the [`MambaMixer`](../../../vllm/model_executor/layers/mamba/mamba_mixer.py) (for Mamba-1) or [`MambaMixer2`](../../../vllm/model_executor/layers/mamba/mamba_mixer2.py) (for Mamba-2) classes.
Please *do not* use the `MambaCacheManager` (deprecated in V1) or replicate any of the V0-specific code paths in the existing model implementations.
V0-only classes and code will be removed in the very near future.
The model should also be added to the `MODELS_CONFIG_MAP` dictionary in [vllm/model_executor/models/config.py](../../../vllm/model_executor/models/config.py) to ensure that the runtime defaults are optimized.
For case (2), we recommend using as a reference the implementation of [`JambaForCausalLM`](../../../vllm/model_executor/models/jamba.py) (for an example of a model that uses Mamba-1 and attention together) or [`BambaForCausalLM`](../../../vllm/model_executor/models/bamba.py) (for an example of a model that uses Mamba-2 and attention together).

3
docs/design/prefix_caching.md
View File

@@ -94,9 +94,6 @@ To improve privacy in shared environments, vLLM supports isolating prefix cache
With this setup, cache sharing is limited to users or requests that explicitly agree on a common salt, enabling cache reuse within a trust group while isolating others.
!!! note
Cache isolation is not supported in engine V0.
## Data Structure
The prefix caching in vLLM v1 is implemented in the KV cache manager. The basic building block is the “Block” data class (simplified):

9
docs/usage/reproducibility.md
View File

@@ -1,10 +1,7 @@
# Reproducibility
vLLM does not guarantee the reproducibility of the results by default, for the sake of performance. You need to do the following to achieve
reproducible results:
- For V1: Turn off multiprocessing to make the scheduling deterministic by setting `VLLM_ENABLE_V1_MULTIPROCESSING=0`.
- For V0: Set the global seed (see below).
vLLM does not guarantee the reproducibility of the results by default, for the sake of performance. To achieve
reproducible results, you need to turn off multiprocessing to make the scheduling deterministic by setting `VLLM_ENABLE_V1_MULTIPROCESSING=0`.
Example: [examples/offline_inference/reproducibility.py](../../examples/offline_inference/reproducibility.py)
@@ -30,8 +27,6 @@ However, in some cases, setting the seed will also [change the random state in u
### Default Behavior
In V0, the `seed` parameter defaults to `None`. When the `seed` parameter is `None`, the random states for `random`, `np.random`, and `torch.manual_seed` are not set. This means that each run of vLLM will produce different results if `temperature > 0`, as expected.
In V1, the `seed` parameter defaults to `0` which sets the random state for each worker, so the results will remain consistent for each vLLM run even if `temperature > 0`.
!!! note

2
docs/usage/v1_guide.md
View File

@@ -2,7 +2,7 @@
!!! announcement
We have started the process of deprecating V0. Please read [RFC #18571](https://github.com/vllm-project/vllm/issues/18571) for more details.
We have fully deprecated 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).