[Chore] Rename SchedulerConfig.chunked_prefill_enabled (#28735)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
@@ -497,7 +497,7 @@ class Scheduler(SchedulerInterface):
|
||||
# chunked prefill has to be enabled explicitly to allow
|
||||
# pooling requests to be chunked
|
||||
if (
|
||||
not self.scheduler_config.chunked_prefill_enabled
|
||||
not self.scheduler_config.enable_chunked_prefill
|
||||
and num_new_tokens > token_budget
|
||||
):
|
||||
self.waiting.pop_request()
|
||||
|
||||
@@ -124,7 +124,7 @@ class EngineCore:
|
||||
# Encoder models without KV cache don't support
|
||||
# chunked prefill. But do SSM models?
|
||||
logger.info("Disabling chunked prefill for model without KVCache")
|
||||
vllm_config.scheduler_config.chunked_prefill_enabled = False
|
||||
vllm_config.scheduler_config.enable_chunked_prefill = False
|
||||
|
||||
scheduler_block_size = (
|
||||
vllm_config.cache_config.block_size
|
||||
|
||||
@@ -2031,7 +2031,7 @@ class GPUModelRunner(
|
||||
|
||||
supported_tasks = list(model.pooler.get_supported_tasks())
|
||||
|
||||
if self.scheduler_config.chunked_prefill_enabled:
|
||||
if self.scheduler_config.enable_chunked_prefill:
|
||||
if "token_embed" in supported_tasks:
|
||||
supported_tasks.remove("token_embed")
|
||||
if "token_classify" in supported_tasks:
|
||||
@@ -3825,7 +3825,7 @@ class GPUModelRunner(
|
||||
supported_pooling_tasks = self.get_supported_pooling_tasks()
|
||||
|
||||
if not supported_pooling_tasks:
|
||||
if self.scheduler_config.chunked_prefill_enabled:
|
||||
if self.scheduler_config.enable_chunked_prefill:
|
||||
raise RuntimeError(
|
||||
f"Model {self.model_config.model} does not support "
|
||||
"any pooling tasks with chunked prefill enabled. "
|
||||
|
||||
Reference in New Issue
Block a user