xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-03-27 09:12:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

update

Browse Source 
Signed-off-by: shen-shanshan <467638484@qq.com>
This commit is contained in:
shen-shanshan 2025-12-24 06:41:36 +00:00
parent a2c7852e4c
commit 7fdd6a11fa
1 changed files with 60 additions and 38 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

98
docs/design/custom_op.md
View File

@ -59,74 +59,96 @@ For example:
**1. Attention:**
--8<-- "../../vllm/attention/layers/mm_encoder_attention.py:mm_encoder_attn"
--8<-- "../../vllm/model_executor/layers/mla.py:multi_head_latent_attention"
```python
--8<-- "vllm/attention/layers/mm_encoder_attention.py:mm_encoder_attn"
--8<-- "vllm/model_executor/layers/mla.py:multi_head_latent_attention"
```
**2. Activation:**
--8<-- "../../vllm/model_executor/layers/activation.py:silu_and_mul"
--8<-- "../../vllm/model_executor/layers/activation.py:mul_and_silu"
--8<-- "../../vllm/model_executor/layers/activation.py:gelu_new"
--8<-- "../../vllm/model_executor/layers/activation.py:gelu_fast"
--8<-- "../../vllm/model_executor/layers/activation.py:quick_gelu"
--8<-- "../../vllm/model_executor/layers/activation.py:gelu_and_mul"
--8<-- "../../vllm/model_executor/layers/activation.py:gelu_and_mul_sparse"
--8<-- "../../vllm/model_executor/layers/activation.py:relu2"
--8<-- "../../vllm/model_executor/layers/activation.py:xielu"
--8<-- "../../vllm/model_executor/layers/activation.py:swigluoai_and_mul"
--8<-- "../../vllm/model_executor/layers/activation.py:fatrelu_and_mul"
```python
--8<-- "vllm/model_executor/layers/activation.py:silu_and_mul"
--8<-- "vllm/model_executor/layers/activation.py:mul_and_silu"
--8<-- "vllm/model_executor/layers/activation.py:gelu_new"
--8<-- "vllm/model_executor/layers/activation.py:gelu_fast"
--8<-- "vllm/model_executor/layers/activation.py:quick_gelu"
--8<-- "vllm/model_executor/layers/activation.py:gelu_and_mul"
--8<-- "vllm/model_executor/layers/activation.py:gelu_and_mul_sparse"
--8<-- "vllm/model_executor/layers/activation.py:relu2"
--8<-- "vllm/model_executor/layers/activation.py:xielu"
--8<-- "vllm/model_executor/layers/activation.py:swigluoai_and_mul"
--8<-- "vllm/model_executor/layers/activation.py:fatrelu_and_mul"
```
**3. MM-Conv:**
--8<-- "../../vllm/model_executor/layers/conv.py:conv2d"
--8<-- "../../vllm/model_executor/layers/conv.py:conv3d"
```python
--8<-- "vllm/model_executor/layers/conv.py:conv2d"
--8<-- "vllm/model_executor/layers/conv.py:conv3d"
```
**4. Embedding:**
--8<-- "../../vllm/model_executor/layers/vocab_parallel_embedding.py:vocab_parallel_embedding"
--8<-- "../../vllm/model_executor/layers/vocab_parallel_embedding.py:parallel_lm_head"
```python
--8<-- "vllm/model_executor/layers/vocab_parallel_embedding.py:vocab_parallel_embedding"
--8<-- "vllm/model_executor/layers/vocab_parallel_embedding.py:parallel_lm_head"
```
**5. Linear:**
--8<-- "../../vllm/model_executor/layers/linear.py:row_parallel_linear"
--8<-- "../../vllm/model_executor/layers/linear.py:row_parallel_linear:column_parallel_linear"
--8<-- "../../vllm/model_executor/layers/linear.py:row_parallel_linear:replicated_linear"
```python
--8<-- "vllm/model_executor/layers/linear.py:row_parallel_linear"
--8<-- "vllm/model_executor/layers/linear.py:row_parallel_linear:column_parallel_linear"
--8<-- "vllm/model_executor/layers/linear.py:row_parallel_linear:replicated_linear"
```
**6. Logits Processor:**
--8<-- "../../vllm/model_executor/layers/logits_processor.py:logits_processor"
```python
--8<-- "vllm/model_executor/layers/logits_processor.py:logits_processor"
```
**7. Mamba:**
--8<-- "../../vllm/model_executor/layers/mamba/mamba_mixer.py:mamba_mixer"
--8<-- "../../vllm/model_executor/layers/mamba/mamba_mixer2.py:mamba_mixer2"
--8<-- "../../vllm/model_executor/layers/mamba/mamba_mixer2.py:mixer2_gated_rms_norm"
--8<-- "../../vllm/model_executor/models/plamo2.py:plamo2_mamba_mixer"
--8<-- "../../vllm/model_executor/layers/mamba/short_conv.py:short_conv"
```python
--8<-- "vllm/model_executor/layers/mamba/mamba_mixer.py:mamba_mixer"
--8<-- "vllm/model_executor/layers/mamba/mamba_mixer2.py:mamba_mixer2"
--8<-- "vllm/model_executor/layers/mamba/mamba_mixer2.py:mixer2_gated_rms_norm"
--8<-- "vllm/model_executor/models/plamo2.py:plamo2_mamba_mixer"
--8<-- "vllm/model_executor/layers/mamba/short_conv.py:short_conv"
```
**8. MoE:**
--8<-- "../../vllm/model_executor/layers/fused_moe/layer.py:fused_moe"
--8<-- "../../vllm/model_executor/layers/fused_moe/fused_moe_modular_method.py:modular_fused_moe"
--8<-- "../../vllm/model_executor/layers/fused_moe/unquantized_fused_moe_method.py:unquantized_fused_moe"
--8<-- "../../vllm/model_executor/models/transformers/moe.py:transformers_fused_moe"
--8<-- "../../vllm/model_executor/layers/fused_moe/fused_moe.py:grouped_topk"
```python
--8<-- "vllm/model_executor/layers/fused_moe/layer.py:fused_moe"
--8<-- "vllm/model_executor/layers/fused_moe/fused_moe_modular_method.py:modular_fused_moe"
--8<-- "vllm/model_executor/layers/fused_moe/unquantized_fused_moe_method.py:unquantized_fused_moe"
--8<-- "vllm/model_executor/models/transformers/moe.py:transformers_fused_moe"
--8<-- "vllm/model_executor/layers/fused_moe/fused_moe.py:grouped_topk"
```
**9. Norm:**
--8<-- "../../vllm/model_executor/layers/layernorm.py:rms_norm"
--8<-- "../../vllm/model_executor/layers/layernorm.py:rms_norm_gated"
--8<-- "../../vllm/model_executor/layers/layernorm.py:gemma_rms_norm"
```python
--8<-- "vllm/model_executor/layers/layernorm.py:rms_norm"
--8<-- "vllm/model_executor/layers/layernorm.py:rms_norm_gated"
--8<-- "vllm/model_executor/layers/layernorm.py:gemma_rms_norm"
```
**10. Quantization:**
--8<-- "../../vllm/model_executor/layers/quantization/input_quant_fp8.py:quant_fp8"
```python
--8<-- "vllm/model_executor/layers/quantization/input_quant_fp8.py:quant_fp8"
```
**11. Rope:**
--8<-- "../../vllm/model_executor/layers/rotary_embedding/base.py:rotary_embedding"
--8<-- "../../vllm/model_executor/layers/rotary_embedding/dual_chunk_rope.py:dual_chunk_rotary_embedding"
--8<-- "../../vllm/model_executor/layers/rotary_embedding/common.py:apply_rotary_emb"
```python
--8<-- "vllm/model_executor/layers/rotary_embedding/base.py:rotary_embedding"
--8<-- "vllm/model_executor/layers/rotary_embedding/dual_chunk_rope.py:dual_chunk_rotary_embedding"
--8<-- "vllm/model_executor/layers/rotary_embedding/common.py:apply_rotary_emb"
```
## Guidelines for Implementing a New CustomOp