Yishuo Wang 54cc9353db support and optimize minicpm-v-2_6 (#11738)		2024-08-07 18:21:16 +08:00
..
awq
gguf	IPEX Duplicate importer V2 (#11310)	2024-06-19 16:29:19 +08:00
layers
models	support and optimize minicpm-v-2_6 (#11738)	2024-08-07 18:21:16 +08:00
npu_models	Fix qwen2 & int4 on NPU (#11646)	2024-07-24 13:14:39 +08:00
__init__.py	Refactor fastapi-serving and add one card serving(#11581)	2024-07-17 11:12:43 +08:00
bmm.py
convert.py	support and optimize minicpm-v-2_6 (#11738)	2024-08-07 18:21:16 +08:00
convert_ipex.py
embedding.py	add save_low_bit support for DiskEmbedding (#11621)	2024-07-19 10:34:53 +08:00
kv.py	Fix MTL 4k input qwen2 compresskv error (#11734)	2024-08-07 16:21:57 +08:00
lisa.py
load_config.yaml
loader.py
lookup.py
low_bit_linear.py	Add disk_embedding parameter to support put Embedding layer on CPU (#11617)	2024-07-18 17:06:06 +08:00
model.py	Fix Pipeline Parallel dtype (#11623)	2024-07-19 13:07:40 +08:00
modelling_bigdl.py
npu_model.py	Clean npu dtype branch (#11515)	2024-07-05 15:45:26 +08:00
pipeline_parallel.py	Optimizations for Pipeline Parallel Serving (#11702)	2024-08-02 12:06:59 +08:00
qlora.py
relora.py
speculative.py
streamer.py
training_patch.py
utils.py	add fallback for unsupported k-quants (#11691)	2024-07-31 11:39:58 +08:00
xpu_customize_fwd.py