mirror of
https://github.com/FlashML-org/FreeToken.git
synced 2026-11-22 08:46:51 +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>
24 lines
631 B
Diff
24 lines
631 B
Diff
--- a/gguf-py/gguf/__init__.py
|
|
+++ b/gguf-py/gguf/__init__.py
|
|
@@ -1,9 +1,4 @@
|
|
from .constants import *
|
|
from .lazy import *
|
|
from .gguf_reader import *
|
|
-from .gguf_writer import *
|
|
from .quants import *
|
|
-from .tensor_mapping import *
|
|
-from .vocab import *
|
|
-from .utility import *
|
|
-from .metadata import *
|
|
--- a/gguf-py/gguf/gguf_reader.py
|
|
+++ b/gguf-py/gguf/gguf_reader.py
|
|
@@ -21,7 +21,7 @@
|
|
# Allow running file in package as a script.
|
|
sys.path.insert(0, str(Path(__file__).parent.parent))
|
|
|
|
-from gguf.constants import (
|
|
+from .constants import (
|
|
GGML_MAX_DIMS,
|
|
GGML_QUANT_SIZES,
|
|
GGUF_DEFAULT_ALIGNMENT,
|