[Spec Decode] Remove Medusa and MLP speculator support (#61701)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 5.5
parent
273a04964e
commit
8530aed2b7
@@ -2669,7 +2669,6 @@ steps:
|
||||
working_dir: "/vllm-workspace/tests"
|
||||
source_file_dependencies:
|
||||
- vllm/v1/spec_decode/
|
||||
- vllm/model_executor/models/mlp_speculator.py
|
||||
- tests/v1/spec_decode/test_acceptance_length.py
|
||||
- vllm/platforms/rocm.py
|
||||
commands:
|
||||
@@ -5978,7 +5977,6 @@ steps:
|
||||
- vllm/model_executor/models/gemma4_mtp.py
|
||||
- vllm/model_executor/models/llama.py
|
||||
- vllm/model_executor/models/llama_eagle3.py
|
||||
- vllm/model_executor/models/medusa.py
|
||||
- vllm/model_executor/models/registry.py
|
||||
- tests/evals/gsm8k/
|
||||
- tests/utils.py
|
||||
|
||||
@@ -841,7 +841,6 @@ steps:
|
||||
working_dir: "/vllm-workspace/tests"
|
||||
source_file_dependencies:
|
||||
- vllm/v1/spec_decode/
|
||||
- vllm/model_executor/models/mlp_speculator.py
|
||||
- tests/v1/spec_decode/test_acceptance_length.py
|
||||
commands:
|
||||
- export VLLM_ALLOW_INSECURE_SERIALIZATION=1
|
||||
@@ -857,6 +856,5 @@ steps:
|
||||
working_dir: /vllm-workspace/tests
|
||||
source_file_dependencies:
|
||||
- vllm/v1/spec_decode/
|
||||
- vllm/model_executor/models/mlp_speculator.py
|
||||
- tests/v1/spec_decode/test_acceptance_length.py
|
||||
- vllm/platforms/rocm.py
|
||||
|
||||
@@ -594,7 +594,6 @@ steps:
|
||||
- vllm/model_executor/models/gemma4_mtp.py
|
||||
- vllm/model_executor/models/llama.py
|
||||
- vllm/model_executor/models/llama_eagle3.py
|
||||
- vllm/model_executor/models/medusa.py
|
||||
- vllm/model_executor/models/registry.py
|
||||
- tests/evals/gsm8k/
|
||||
- tests/utils.py
|
||||
|
||||
Reference in New Issue
Block a user