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

[Doc] Compatibility matrix for mutual exclusive features (#8512)

Browse Source 
Signed-off-by: Wallas Santos <wallashss@ibm.com>
This commit is contained in:
Wallas Henrique
2024-10-11 15:18:50 -03:00
committed by GitHub
parent 1a1823871d
commit 8baf85e4e9
13 changed files with 467 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/executor/cpu_executor.py
View File

@@ -28,6 +28,8 @@ class CPUExecutor(ExecutorBase):
def _init_executor(self) -> None:
assert self.device_config.device_type == "cpu"
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# If the feature combo become valid
assert self.lora_config is None, "cpu backend doesn't support LoRA"
#
@@ -324,6 +326,8 @@ def _verify_and_get_model_config(config: ModelConfig) -> ModelConfig:
if config.dtype == torch.float16:
logger.warning("float16 is not supported on CPU, casting to bfloat16.")
config.dtype = torch.bfloat16
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# If the feature combo become valid
if not config.enforce_eager:
logger.warning(
"CUDA graph is not supported on CPU, fallback to the eager "
@@ -334,6 +338,8 @@ def _verify_and_get_model_config(config: ModelConfig) -> ModelConfig:
def _verify_and_get_scheduler_config(
config: SchedulerConfig) -> SchedulerConfig:
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# If the feature combo become valid
if config.chunked_prefill_enabled:
logger.warning("Chunked prefill is not supported on CPU, disable it.")
config.chunked_prefill_enabled = False
@@ -342,6 +348,8 @@ def _verify_and_get_scheduler_config(
def _verify_and_get_cache_config(config: CacheConfig) -> CacheConfig:
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
# If the feature combo become valid
if config.enable_prefix_caching:
logger.warning("Prefix caching is not supported on CPU, disable it.")
config.enable_prefix_caching = False