[Quantization] Deprecate Long Tail of Schemes (#31688)
Signed-off-by: Robert Shaw <robshaw@redhat.com> Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com> Co-authored-by: Robert Shaw <robshaw@redhat.com> Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
This commit is contained in:
co-authored by
Robert Shaw
Wentao Ye
parent
d62cfe546d
commit
5825bbc1f7
@@ -451,6 +451,7 @@ class EngineArgs:
|
||||
hf_overrides: HfOverrides = get_field(ModelConfig, "hf_overrides")
|
||||
tokenizer_revision: str | None = ModelConfig.tokenizer_revision
|
||||
quantization: QuantizationMethods | None = ModelConfig.quantization
|
||||
allow_deprecated_quantization: bool = ModelConfig.allow_deprecated_quantization
|
||||
enforce_eager: bool = ModelConfig.enforce_eager
|
||||
disable_custom_all_reduce: bool = ParallelConfig.disable_custom_all_reduce
|
||||
limit_mm_per_prompt: dict[str, int | dict[str, int]] = get_field(
|
||||
@@ -648,6 +649,10 @@ class EngineArgs:
|
||||
)
|
||||
model_group.add_argument("--max-model-len", **model_kwargs["max_model_len"])
|
||||
model_group.add_argument("--quantization", "-q", **model_kwargs["quantization"])
|
||||
model_group.add_argument(
|
||||
"--allow-deprecated-quantization",
|
||||
**model_kwargs["allow_deprecated_quantization"],
|
||||
)
|
||||
model_group.add_argument("--enforce-eager", **model_kwargs["enforce_eager"])
|
||||
model_group.add_argument("--max-logprobs", **model_kwargs["max_logprobs"])
|
||||
model_group.add_argument("--logprobs-mode", **model_kwargs["logprobs_mode"])
|
||||
@@ -1225,6 +1230,7 @@ class EngineArgs:
|
||||
tokenizer_revision=self.tokenizer_revision,
|
||||
max_model_len=self.max_model_len,
|
||||
quantization=self.quantization,
|
||||
allow_deprecated_quantization=self.allow_deprecated_quantization,
|
||||
enforce_eager=self.enforce_eager,
|
||||
max_logprobs=self.max_logprobs,
|
||||
logprobs_mode=self.logprobs_mode,
|
||||
|
||||
Reference in New Issue
Block a user