[Migration] Migrate GGUF quantization support to plugin (#39612)

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
This commit is contained in:
Isotr0py
2026-06-12 12:02:21 -07:00
committed by GitHub
parent d6fd7ce8da
commit 6635279d8a
57 changed files with 72 additions and 9048 deletions
@@ -39,12 +39,6 @@ def models_list(*, all: bool = True, keywords: list[str] | None = None):
]
)
# TODO: figure out why this fails.
if False and is_quant_method_supported("gguf"): # noqa: SIM223
TEST_MODELS.append(
("TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF", {"quantization": "gguf"})
)
if is_quant_method_supported("gptq"):
TEST_MODELS.append(
("TheBloke/TinyLlama-1.1B-Chat-v0.3-GPTQ", {"quantization": "gptq"})