mirror of
https://github.com/FlashML-org/FreeToken.git
synced 2026-11-21 01:52:30 +08:00
* build(kernel): vendor ggml-cuda from llama.cpp 8c2134a8 behind a tvm-ffi binding * build(deps): vendor the gguf-py reader * feat(quant): add the GGUF quant kind and an embedding quant method * feat(gguf): serve Flash-Next and Gemma4 GGUF on the GGUF quant kind and drop the old Q4_0 path * fix(kernel): build ggml-cuda for plain sm_120 by turning off the native fp4 MMA * perf(gguf): write ggml results in the activation dtype and keep MoE intermediates in bf16 * build(kernel): compress the ggml fatbin to keep the multi-arch kernel cache small * fix(gguf): read F32, F16 and BF16 PLE tables without ggml * fix(moe): pad the offload slot cache for ggml MMQ tail reads * fix(gguf): support hip builds and runtime devices * fix(gguf): copy same-type dequantize and check for missing ggml converters * fix(gguf): load quantized qwen4exp ple_key and ple_value * feat(gguf): run float parts of a fused GGUF linear as bf16 segments * fix(gguf): load quantized qwen4exp hyper-connection and gdn ba weights * fix(moe): zero the prefill staging area after the last prefill layer --------- Co-authored-by: zihaomu <zihaomu@outlook.com>
15 lines
657 B
Python
15 lines
657 B
Python
from .base import LinearConfig, LinearKernel, LinearMethod
|
|
from . import fp8_block, fp8_tensor, gguf, mxfp8, nvfp4, unquantized
|
|
from .fp8_block import Fp8BlockLinearMethod
|
|
from .fp8_tensor import Fp8TensorLinearMethod
|
|
from .mxfp8 import Mxfp8LinearMethod
|
|
from .nvfp4 import Nvfp4LinearMethod
|
|
from .unquantized import UnquantizedLinearMethod
|
|
from .gguf import GGUFLinearMethod
|
|
|
|
__all__ = [
|
|
"LinearConfig", "LinearKernel", "LinearMethod",
|
|
"UnquantizedLinearMethod", "Fp8TensorLinearMethod", "Fp8BlockLinearMethod", "Mxfp8LinearMethod", "Nvfp4LinearMethod", "GGUFLinearMethod",
|
|
"fp8_block", "fp8_tensor", "gguf", "mxfp8", "nvfp4", "unquantized",
|
|
]
|