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

[Bugfix] Fix new Llama3.1 GGUF model loading (#7269)

Browse Source
This commit is contained in:
Isotr0py 2024-08-09 04:42:44 +08:00 committed by GitHub
parent e904576743
commit 8334c39f37
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 15 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/model_loader/weight_utils.py
View File

@ -435,6 +435,7 @@ def gguf_quant_weights_iterator(
reader = gguf.GGUFReader(gguf_file) reader = gguf.GGUFReader(gguf_file)
for tensor in reader.tensors: for tensor in reader.tensors:
if tensor.name in gguf_to_hf_name_map:
weight_type = tensor.tensor_type weight_type = tensor.tensor_type
name = gguf_to_hf_name_map[tensor.name] name = gguf_to_hf_name_map[tensor.name]
@ -444,6 +445,7 @@ def gguf_quant_weights_iterator(
yield weight_type_name, weight_type yield weight_type_name, weight_type
for tensor in reader.tensors: for tensor in reader.tensors:
if tensor.name in gguf_to_hf_name_map:
weight = tensor.data weight = tensor.data
weight_type = tensor.tensor_type weight_type = tensor.tensor_type
name = gguf_to_hf_name_map[tensor.name] name = gguf_to_hf_name_map[tensor.name]