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

28
vllm/model_executor/model_loader/weight_utils.py
View File

@ -435,23 +435,25 @@ def gguf_quant_weights_iterator(
reader = gguf.GGUFReader(gguf_file)
for tensor in reader.tensors:
weight_type = tensor.tensor_type
name = gguf_to_hf_name_map[tensor.name]
if tensor.name in gguf_to_hf_name_map:
weight_type = tensor.tensor_type
name = gguf_to_hf_name_map[tensor.name]
if weight_type.name != "F32":
weight_type_name = name.replace("weight", "qweight_type")
weight_type = torch.tensor(weight_type)
yield weight_type_name, weight_type
if weight_type.name != "F32":
weight_type_name = name.replace("weight", "qweight_type")
weight_type = torch.tensor(weight_type)
yield weight_type_name, weight_type
for tensor in reader.tensors:
weight = tensor.data
weight_type = tensor.tensor_type
name = gguf_to_hf_name_map[tensor.name]
if tensor.name in gguf_to_hf_name_map:
weight = tensor.data
weight_type = tensor.tensor_type
name = gguf_to_hf_name_map[tensor.name]
if weight_type.name != "F32":
name = name.replace("weight", "qweight")
param = torch.tensor(weight)
yield name, param
if weight_type.name != "F32":
name = name.replace("weight", "qweight")
param = torch.tensor(weight)
yield name, param
def kv_cache_scales_loader(