Update Dockerfile.ci to install vLLM wheel version 3dd142adb7f7fa3b0b8345ee046ba36a12d9e530 and remove ExtractHiddenStatesProposer references from GPU model runners for cleaner code.
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
This commit is contained in:
1 parent
2398a7c1d7
commit
4914466f0b
4 files changed
+8
-15
No files matched your search
@@ -25,7 +25,6 @@ from vllm.v1.core.sched.output import GrammarOutput, SchedulerOutput
|
||||
from vllm.v1.outputs import AsyncModelRunnerOutput, make_empty_encoder_model_runner_output
|
||||
from vllm.v1.spec_decode.draft_model import DraftModelProposer
|
||||
from vllm.v1.spec_decode.eagle import EagleProposer
|
||||
from vllm.v1.spec_decode.extract_hidden_states import ExtractHiddenStatesProposer
|
||||
from vllm.v1.utils import record_function_or_nullcontext
|
||||
from vllm.v1.worker.gpu_model_runner import (
|
||||
EMPTY_MODEL_RUNNER_OUTPUT,
|
||||
@@ -727,13 +726,11 @@ class GPUGenerationModelRunner(OmniGPUModelRunner):
|
||||
hidden_states = outputs
|
||||
hidden_states, multimodal_outputs = self.extract_multimodal_outputs(hidden_states)
|
||||
if self.speculative_config and (
|
||||
self.speculative_config.use_eagle()
|
||||
or self.speculative_config.uses_draft_model()
|
||||
or self.speculative_config.uses_extract_hidden_states()
|
||||
self.speculative_config.use_eagle() or self.speculative_config.uses_draft_model()
|
||||
):
|
||||
assert isinstance(
|
||||
self.drafter,
|
||||
EagleProposer | DraftModelProposer | ExtractHiddenStatesProposer,
|
||||
EagleProposer | DraftModelProposer,
|
||||
)
|
||||
assert self.speculative_config is not None
|
||||
# Eagle currently only supports PIECEWISE cudagraphs.
|
||||
|
||||
Reference in new issue
Block a user