xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-13 18:25:40 +08:00
Code Issues Packages Projects Releases Wiki Activity

[DOC] fix doc typos (#19600)

Browse Source 
Signed-off-by: Di Liu <liu-di@sjtu.edu.cn>
This commit is contained in:
Di Liu 2025-06-17 11:34:53 +08:00 committed by GitHub
parent ede5c4ebdf
commit 5b3ad5ecf2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/model_executor/layers/vocab_parallel_embedding.py
View File

@ -176,17 +176,17 @@ class VocabParallelEmbedding(torch.nn.Module):
Therefore, the tensor format looks like the following: Therefore, the tensor format looks like the following:
TP1, rank 0 (no sharding): TP1, rank 0 (no sharding):
|< --------BASE-------- >|< -BASE PADDING-- >|< -----LORA------ >|< -LORA PADDING-- >| |< --------BASE-------- >|< -BASE PADDING-- >|< -----LORA------ >|< -LORA PADDING-- >|
corresponding token_id: | 0 | 1 | ... | 1009 | -1 | ... | -1 | 1010 | ... | 1015 | -1 | ... | -1 | corresponding token_id: | 0 | 1 | ... | 1009 | -1 | ... | -1 | 1010 | ... | 1025 | -1 | ... | -1 |
index: | 0 | 1 | ... | 1009 | 1010 | ... | 1023 | 1024 | ... | 1039 | 1040 | ... | 1087 | index: | 0 | 1 | ... | 1009 | 1010 | ... | 1023 | 1024 | ... | 1039 | 1040 | ... | 1087 |
TP2, rank 0: TP2, rank 0:
|< --------------------BASE--------------------- >|< -----LORA------ >|< -LORA PADDING- >| |< --------------------BASE--------------------- >|< -----LORA------ >|< -LORA PADDING- >|
corresponding token_id: | 0 | 1 | 2 | ... | 497 | 498 | ... | 511 | 1000 | ... | 1015 | -1 | ... | -1 | corresponding token_id: | 0 | 1 | 2 | ... | 497 | 498 | ... | 511 | 1010 | ... | 1025 | -1 | ... | -1 |
index: | 0 | 1 | 2 | ... | 497 | 498 | ... | 511 | 512 | ... | 527 | 520 | ... | 543 | index: | 0 | 1 | 2 | ... | 497 | 498 | ... | 511 | 512 | ... | 527 | 528 | ... | 543 |
TP2, rank 1: TP2, rank 1:
|< -----------BASE----------- >|< -BASE PADDING- >|< -----------LORA PADDING----------- >| |< -----------BASE----------- >|< -BASE PADDING- >|< -----------LORA PADDING----------- >|
corresponding token_id: | 512 | 513 | 514 | ... | 1009 | -1 | ... | -1 | -1 | ... | -1 | -1 | ... | -1 | corresponding token_id: | 512 | 513 | 514 | ... | 1009 | -1 | ... | -1 | -1 | ... | -1 | -1 | ... | -1 |
index: | 0 | 1 | 2 | ... | 497 | 498 | ... | 511 | 512 | ... | 519 | 520 | ... | 543 | index: | 0 | 1 | 2 | ... | 497 | 498 | ... | 511 | 512 | ... | 527 | 528 | ... | 543 |
Args: Args:
num_embeddings: vocabulary size. num_embeddings: vocabulary size.