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

[docs] fix unintentional misspellings (#33863)

Browse Source 
Signed-off-by: rinbaro <ilgomishra@gmail.com>
This commit is contained in:
rinbaro
2026-02-04 20:50:59 -08:00
committed by GitHub
parent add9f1fbd9
commit 007b183d74
3 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -138,7 +138,7 @@ These models should follow the same instructions as case (1), but they should in
For case (3), we recommend looking at the implementation of [`MiniMaxText01ForCausalLM`](../../../vllm/model_executor/models/minimax_text_01.py) or [`Lfm2ForCausalLM`](../../../vllm/model_executor/models/lfm2.py) as a reference, which use custom "mamba-like" layers `MiniMaxText01LinearAttention` and `ShortConv` respectively.
Please follow the same guidelines as case (2) for implementing these models.
We use "mamba-like" to refer to layers that posses a state that is updated in-place, rather than being appended-to (like KV cache for attention).
We use "mamba-like" to refer to layers that possess a state that is updated in-place, rather than being appended-to (like KV cache for attention).
For implementing new custom mamba-like layers, one should inherit from `MambaBase` and implement the methods `get_state_dtype`, `get_state_shape` to calculate the data types and state shapes at runtime, as well as `mamba_type` and `get_attn_backend`.
It is also necessary to implement the "attention meta-data" class which handles the meta-data that is common across all layers.
Please see [`LinearAttentionMetadata`](../../../vllm/v1/attention/backends/linear_attn.py) or [`ShortConvAttentionMetadata`](../../../vllm/v1/attention/backends/short_conv_attn.py) for examples of this.