[Bugfix][Spec Decode] Fix eagle3 first-layer qkv_proj prefix for quantized drafts (#48068)
Signed-off-by: zixi-qi <zixi@inferact.ai> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 4.8
parent
3935829f89
commit
2db39c7049
@@ -60,7 +60,7 @@ class LlamaDecoderLayer(LlamaDecoderLayer):
|
||||
self.self_attn.total_num_kv_heads,
|
||||
bias=qkv_bias,
|
||||
quant_config=quant_config,
|
||||
prefix=maybe_prefix(prefix, "qkv_proj"),
|
||||
prefix=maybe_prefix(prefix, "self_attn.qkv_proj"),
|
||||
)
|
||||
|
||||
self.hidden_norm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
|
||||
|
||||
Reference in New Issue
Block a user