[Quantization] Rework quantization_config to use QuantKey and allow for activation override (#41566)

This commit is contained in:
Michael Goin
2026-05-13 16:58:32 -04:00
committed by GitHub
parent cca32d55a2
commit 8efd508204
16 changed files with 621 additions and 322 deletions
+2 -4
View File
@@ -35,7 +35,7 @@ from vllm.config.model import (
TokenizerMode,
)
from vllm.config.quantization import (
OnlineQuantizationConfigArgs,
QuantizationConfigArgs,
)
from vllm.distributed.weight_transfer.base import (
WeightTransferInitRequest,
@@ -248,9 +248,7 @@ class LLM:
attention_config: dict[str, Any] | AttentionConfig | None = None,
kv_cache_memory_bytes: int | None = None,
compilation_config: int | dict[str, Any] | CompilationConfig | None = None,
quantization_config: dict[str, Any]
| OnlineQuantizationConfigArgs
| None = None,
quantization_config: dict[str, Any] | QuantizationConfigArgs | None = None,
logits_processors: list[str | type[LogitsProcessor]] | None = None,
**kwargs: Any,
) -> None: