biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Doc][2/N] Reorganize Models and Usage sections (#11755)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2025-01-06 21:40:31 +08:00
committed by GitHub
parent 996357e480
commit ee77fdb5de
45 changed files with 265 additions and 238 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/config.py
View File

@@ -644,7 +644,7 @@ class ModelConfig:
self.use_async_output_proc = False
return
# Reminder: Please update docs/source/usage/compatibility_matrix.md
# Reminder: Please update docs/source/features/compatibility_matrix.md
# If the feature combo become valid
from vllm.platforms import current_platform
if not current_platform.is_async_output_supported(self.enforce_eager):
@@ -665,7 +665,7 @@ class ModelConfig:
if self.runner_type == "pooling":
self.use_async_output_proc = False
# Reminder: Please update docs/source/usage/compatibility_matrix.md
# Reminder: Please update docs/source/features/compatibility_matrix.md
# If the feature combo become valid
if speculative_config:
logger.warning("Async output processing is not supported with"
@@ -2064,7 +2064,7 @@ class LoRAConfig:
model_config.quantization)
def verify_with_scheduler_config(self, scheduler_config: SchedulerConfig):
# Reminder: Please update docs/source/usage/compatibility_matrix.md
# Reminder: Please update docs/source/features/compatibility_matrix.md
# If the feature combo become valid
if scheduler_config.chunked_prefill_enabled:
logger.warning("LoRA with chunked prefill is still experimental "