[Core] structured generation mode for DiffusionGemma model (Jev-like) (#57250)
Signed-off-by: Matt Mastracci <matthew@mastracci.com> Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com> Signed-off-by: Razorback16 <razorback16@protonmail.com> Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com> Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com> Co-authored-by: Codex <noreply@openai.com> Co-authored-by: Razorback16 <razorback16@protonmail.com>
This commit is contained in:
co-authored by
Claude Fable 5.1
Lucas Wilkinson
Codex
Razorback16
parent
fae5cbfc8b
commit
1b3b88ec2b
+12
-1
@@ -7,6 +7,7 @@ import vllm.envs as envs
|
||||
from tests.v1.kv_connector.unit.utils import MockKVConfig
|
||||
from vllm.config import (
|
||||
CacheConfig,
|
||||
DiffusionConfig,
|
||||
ECTransferConfig,
|
||||
KVTransferConfig,
|
||||
ModelConfig,
|
||||
@@ -77,6 +78,8 @@ def create_scheduler(
|
||||
kv_cache_spec: KVCacheSpec | None = None,
|
||||
per_request_spec_decode_metrics: str = "none",
|
||||
scheduling_policy: SchedulerPolicy = "fcfs",
|
||||
diffusion_canvas_length: int | None = None,
|
||||
scheduler_cls: type[Scheduler] | None = None,
|
||||
) -> Scheduler | AsyncScheduler:
|
||||
"""Create scheduler under test.
|
||||
|
||||
@@ -178,6 +181,12 @@ def create_scheduler(
|
||||
else None
|
||||
)
|
||||
|
||||
diffusion_config: DiffusionConfig | None = None
|
||||
if diffusion_canvas_length is not None:
|
||||
# A diffusion checkpoint declares its canvas in the HF config.
|
||||
model_config.hf_config.canvas_length = diffusion_canvas_length
|
||||
diffusion_config = DiffusionConfig(canvas_length=diffusion_canvas_length)
|
||||
|
||||
vllm_config = VllmConfig(
|
||||
scheduler_config=scheduler_config,
|
||||
model_config=model_config,
|
||||
@@ -188,6 +197,7 @@ def create_scheduler(
|
||||
),
|
||||
kv_transfer_config=kv_transfer_config,
|
||||
speculative_config=speculative_config,
|
||||
diffusion_config=diffusion_config,
|
||||
ec_transfer_config=ec_transfer_config,
|
||||
observability_config=ObservabilityConfig(
|
||||
per_request_spec_decode_metrics=per_request_spec_decode_metrics,
|
||||
@@ -207,7 +217,8 @@ def create_scheduler(
|
||||
)
|
||||
cache_config.num_gpu_blocks = num_blocks
|
||||
register_all_kvcache_specs(vllm_config)
|
||||
scheduler_cls = AsyncScheduler if async_scheduling else Scheduler
|
||||
if scheduler_cls is None:
|
||||
scheduler_cls = AsyncScheduler if async_scheduling else Scheduler
|
||||
scheduler = scheduler_cls(
|
||||
vllm_config=vllm_config,
|
||||
kv_cache_config=kv_cache_config,
|
||||
|
||||
Reference in New Issue
Block a user