Multi-node Tensor Parallelism (#550)

Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
This commit is contained in:
Ying Sheng
2024-06-17 20:41:24 -07:00
committed by GitHub
parent 53a7ebd89a
commit 09593e9bc9
10 changed files with 167 additions and 46 deletions

View File

@@ -71,7 +71,11 @@ class ModelConfig:
return 1
# For DBRX and MPT
if self.hf_config.model_type in ["dbrx", "mpt"]:
if self.hf_config.model_type in ["mpt"]:
if "kv_n_heads" in self.hf_config.attn_config:
return self.hf_config.attn_config["kv_n_heads"]
return self.hf_config.num_attention_heads
if self.hf_config.model_type in ["dbrx"]:
return getattr(
self.hf_config.attn_config,
"kv_n_heads",