ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
ipex-llm/python/llm/src/ipex_llm/transformers
History
Yuwen Hu 9d65dcd7ef
Fix deepseek coder with linear rope type support on GPU (#12709) 
* Fix deepseek coder with linear rope type

* Style fix

* Move to optimize_pre

* Small fix

* Small fix

* Small fix to not affect other cases

* Style fixes

* Update function name

* Small fix

* Small fix

* Small fix

* Fix for low transformers version first

* Style fix

* Small fix
2025-01-15 21:12:34 +08:00
..
awq Refactor bigdl.llm to ipex_llm (#24) 2024-03-22 15:41:21 +08:00
gguf IPEX Duplicate importer V2 (#11310) 2024-06-19 16:29:19 +08:00
models Fix deepseek coder with linear rope type support on GPU (#12709) 2025-01-15 21:12:34 +08:00
npu_models [NPU] Support save npu quantized model without npu dependency (#12647) 2025-01-06 18:06:22 +08:00
npu_pipeline_model [NPU] Further fix saving of generation config (#12657) 2025-01-07 13:53:54 +08:00
__init__.py Add Qwen2-VL HF GPU example with ModelScope Support (#12606) 2025-01-13 15:42:04 +08:00
convert.py Fix deepseek coder with linear rope type support on GPU (#12709) 2025-01-15 21:12:34 +08:00
convert_ipex.py fix user issue (#12692) 2025-01-10 10:18:47 +08:00
embedding.py add save_low_bit support for DiskEmbedding (#11621) 2024-07-19 10:34:53 +08:00
kv.py llama 3.1/3.2 support compresskv (#12347) 2024-11-06 17:33:43 +08:00
lisa.py LISA Finetuning Example (#10743) 2024-04-18 13:48:10 +08:00
load_config.yaml Adding load_low_bit interface for ipex_llm_worker (#11000) 2024-05-13 15:30:19 +08:00
loader.py Remove all ipex usage (#12666) 2025-01-08 10:31:18 +08:00
lookup.py refactor device check and remove cohere/mixtral support (#12659) 2025-01-07 11:15:51 +08:00
low_bit_linear.py LLM: add new qtype woq_int4 to support gemm int4 temporary. (#12706) 2025-01-15 14:41:33 +08:00
model.py Add Qwen2-VL HF GPU example with ModelScope Support (#12606) 2025-01-13 15:42:04 +08:00
modelling_bigdl.py Remove chatglm_C Module to Eliminate LGPL Dependency (#11178) 2024-05-31 17:03:11 +08:00
npu_model.py [NPU ] fix load logic of glm-edge models (#12698) 2025-01-10 16:08:37 +08:00
patches.py Patch sdpa check function in specific module attributes table (#12285) 2024-10-29 18:41:09 +08:00
pipeline_parallel.py Add missing arguments in pipeline parallel generate method (#12142) 2024-11-18 13:50:18 +08:00
qlora.py remove old rope usage (#12552) 2024-12-16 15:59:36 +08:00
relora.py Refactor bigdl.llm to ipex_llm (#24) 2024-03-22 15:41:21 +08:00
speculative.py Remove all ipex usage (#12666) 2025-01-08 10:31:18 +08:00
streamer.py [LLM]Reopen autotp generate_stream (#11120) 2024-05-24 17:16:14 +08:00
training_patch.py Fix error during merging adapter (#11145) 2024-05-27 19:41:42 +08:00
utils.py small fix and remove ununsed code about ipex (#12671) 2025-01-08 17:39:04 +08:00
xpu_customize_fwd.py Refactor bigdl.llm to ipex_llm (#24) 2024-03-22 15:41:21 +08:00
xpu_ops.py fix custom kernel registration (#12674) 2025-01-08 17:39:17 +08:00