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/models
History
Cengguang Zhang cfed76b2ed
LLM: add long-context support for Qwen1.5-7B/Baichuan2-7B/Mistral-7B. (#10937) 
* LLM: add split tensor support for baichuan2-7b and qwen1.5-7b.

* fix style.

* fix style.

* fix style.

* add support for mistral and fix condition threshold.

* fix  style.

* fix comments.
2024-05-10 16:40:15 +08:00
..
__init__.py Refactor bigdl.llm to ipex_llm (#24) 2024-03-22 15:41:21 +08:00
aquila.py LLM: fix get env KV_CACHE_ALLOC_BLOCK_LENGTH type. (#10771) 2024-04-16 09:32:30 +08:00
baichuan.py remove new_layout parameter (#10906) 2024-04-29 10:31:50 +08:00
baichuan2.py LLM: add long-context support for Qwen1.5-7B/Baichuan2-7B/Mistral-7B. (#10937) 2024-05-10 16:40:15 +08:00
bert.py Refactor bigdl.llm to ipex_llm (#24) 2024-03-22 15:41:21 +08:00
bloom.py LLM: fix get env KV_CACHE_ALLOC_BLOCK_LENGTH type. (#10771) 2024-04-16 09:32:30 +08:00
chatglm.py LLM: fix get env KV_CACHE_ALLOC_BLOCK_LENGTH type. (#10771) 2024-04-16 09:32:30 +08:00
chatglm2.py LLM: update split tensor conditions. (#10872) 2024-04-30 17:07:21 +08:00
chatglm2_32k.py LLM: fix get env KV_CACHE_ALLOC_BLOCK_LENGTH type. (#10771) 2024-04-16 09:32:30 +08:00
cohere.py LLM: Optimize cohere model (#10878) 2024-05-07 10:19:50 +08:00
decilm.py LLM: fix get env KV_CACHE_ALLOC_BLOCK_LENGTH type. (#10771) 2024-04-16 09:32:30 +08:00
falcon.py LLM: fix get env KV_CACHE_ALLOC_BLOCK_LENGTH type. (#10771) 2024-04-16 09:32:30 +08:00
gemma.py remove rms norm copy (#10793) 2024-04-19 13:57:48 +08:00
gptbigcode.py Refactor bigdl.llm to ipex_llm (#24) 2024-03-22 15:41:21 +08:00
gptj.py LLM: fix get env KV_CACHE_ALLOC_BLOCK_LENGTH type. (#10771) 2024-04-16 09:32:30 +08:00
gptneox.py LLM: fix get env KV_CACHE_ALLOC_BLOCK_LENGTH type. (#10771) 2024-04-16 09:32:30 +08:00
internlm.py LLM: fix get env KV_CACHE_ALLOC_BLOCK_LENGTH type. (#10771) 2024-04-16 09:32:30 +08:00
llama.py LLM: update split tensor conditions. (#10872) 2024-04-30 17:07:21 +08:00
mistral.py LLM: add long-context support for Qwen1.5-7B/Baichuan2-7B/Mistral-7B. (#10937) 2024-05-10 16:40:15 +08:00
mixtral.py LLM: Add mixtral speculative CPU example (#10830) 2024-04-23 10:05:51 +08:00
mpt.py LLM: fix get env KV_CACHE_ALLOC_BLOCK_LENGTH type. (#10771) 2024-04-16 09:32:30 +08:00
phi.py remove new_layout parameter (#10906) 2024-04-29 10:31:50 +08:00
phi3.py use quantize kv and sdp in phi3-mini (#10973) 2024-05-09 15:16:18 +08:00
phixtral.py Disable fast fused rope on UHD (#10780) 2024-04-18 10:03:53 +08:00
qwen.py remove new_layout parameter (#10906) 2024-04-29 10:31:50 +08:00
qwen2.py LLM: add long-context support for Qwen1.5-7B/Baichuan2-7B/Mistral-7B. (#10937) 2024-05-10 16:40:15 +08:00
qwen2_moe.py use new quantize kv (#10888) 2024-04-26 14:42:17 +08:00
qwen_vl.py Disable fast fused rope on UHD (#10780) 2024-04-18 10:03:53 +08:00
rwkv4.py fix rwkv with pip installer (#10591) 2024-03-29 17:56:45 +08:00
rwkv5.py disable rwkv5 fp16 (#10699) 2024-04-09 16:42:11 +08:00
stablelm.py use new quantize kv (#10888) 2024-04-26 14:42:17 +08:00
starcoder2.py remove new_layout parameter (#10906) 2024-04-29 10:31:50 +08:00
utils.py use fp16_sdp when head_dim=96 (#10976) 2024-05-09 17:02:59 +08:00
yuan.py use new quantize kv (#10888) 2024-04-26 14:42:17 +08:00