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

[Bugfix] Fix compressed-tensors quantization failure for DeepSeek-R1 on MI300x (#36247)

Browse Source 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
This commit is contained in:
vllmellm
2026-03-07 17:26:59 +08:00
committed by GitHub
parent 755356b3d1
commit ee8a29511f
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/model_executor/models/deepseek_v2.py
View File

@@ -756,7 +756,7 @@ direct_register_custom_op(
)
class DeepSeekV2FusedQkvAProj(MergedColumnParallelLinear):
class DeepSeekV2FusedQkvAProjLinear(MergedColumnParallelLinear):
def __init__(
self,
input_size: int,
@@ -848,7 +848,7 @@ class DeepseekV2MLAAttention(nn.Module):
self.max_position_embeddings = max_position_embeddings
if self.q_lora_rank is not None:
self.fused_qkv_a_proj = DeepSeekV2FusedQkvAProj(
self.fused_qkv_a_proj = DeepSeekV2FusedQkvAProjLinear(
self.hidden_size,
[self.q_lora_rank, self.kv_lora_rank + self.qk_rope_head_dim],
quant_config=quant_config,