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

[Doc] Create a new "Usage" section (#10827)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2024-12-05 11:19:35 +08:00
committed by GitHub
parent 8d370e91cb
commit aa39a8e175
25 changed files with 218 additions and 125 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/config.py
View File

@@ -509,7 +509,7 @@ class ModelConfig:
self.use_async_output_proc = False
return
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# Reminder: Please update docs/source/usage/compatibility_matrix.rst
# If the feature combo become valid
if device_config.device_type not in ("cuda", "tpu", "xpu", "hpu"):
logger.warning(
@@ -525,7 +525,7 @@ class ModelConfig:
self.use_async_output_proc = False
return
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# Reminder: Please update docs/source/usage/compatibility_matrix.rst
# If the feature combo become valid
if device_config.device_type == "cuda" and self.enforce_eager:
logger.warning(
@@ -540,7 +540,7 @@ class ModelConfig:
if self.task == "embedding":
self.use_async_output_proc = False
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# Reminder: Please update docs/source/usage/compatibility_matrix.rst
# If the feature combo become valid
if speculative_config:
logger.warning("Async output processing is not supported with"
@@ -1704,7 +1704,7 @@ class LoRAConfig:
model_config.quantization)
def verify_with_scheduler_config(self, scheduler_config: SchedulerConfig):
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# Reminder: Please update docs/source/usage/compatibility_matrix.rst
# If the feature combo become valid
if scheduler_config.chunked_prefill_enabled:
raise ValueError("LoRA is not supported with chunked prefill yet.")