[Spec Decode] Add Qwen3 architecture support for EAGLE3 (#43132)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
This commit is contained in:
@@ -1530,6 +1530,16 @@ _SPECULATIVE_DECODING_EXAMPLE_MODELS = {
|
||||
"Qwen/Qwen3-VL-8B-Instruct",
|
||||
speculative_model="taobao-mnn/Qwen3-VL-8B-Instruct-Eagle3",
|
||||
),
|
||||
"Eagle3Qwen3ForCausalLM": _HfExamplesInfo(
|
||||
"Qwen/Qwen3-8B",
|
||||
trust_remote_code=True,
|
||||
speculative_model=(
|
||||
"inference-optimization/"
|
||||
"Qwen3-8B-from-Qwen3-8B_regen-speculators.eagle3-qwen3arch-ckpt1"
|
||||
),
|
||||
tokenizer="Qwen/Qwen3-8B",
|
||||
use_original_num_layers=True,
|
||||
),
|
||||
# [PEagle]
|
||||
"PEagleDraftModel": _HfExamplesInfo(
|
||||
"Qwen/Qwen3-8B",
|
||||
@@ -1545,6 +1555,15 @@ _SPECULATIVE_DECODING_EXAMPLE_MODELS = {
|
||||
tokenizer="Qwen/Qwen3-8B",
|
||||
use_original_num_layers=True,
|
||||
),
|
||||
"PeagleQwen3ForCausalLM": _HfExamplesInfo(
|
||||
"Qwen/Qwen3-8B",
|
||||
trust_remote_code=True,
|
||||
speculative_model=(
|
||||
"inference-optimization/Qwen3-8B-speculators.peagle-qwen3arch-ckpt4"
|
||||
),
|
||||
tokenizer="Qwen/Qwen3-8B",
|
||||
use_original_num_layers=True,
|
||||
),
|
||||
# [MTP]
|
||||
"DeepSeekMTPModel": _HfExamplesInfo(
|
||||
"luccafong/deepseek_mtp_main_random",
|
||||
|
||||
Reference in New Issue
Block a user