| .. |
|
__init__.py
|
optimize llama npu perf (#11426)
|
2024-06-25 17:43:20 +08:00 |
|
baichuan.py
|
fix baichuan (#11606)
|
2024-07-18 09:43:36 +08:00 |
|
baichuan_mp.py
|
Refactor NPU baichuan multiple-process (#11945)
|
2024-08-28 11:33:40 -07:00 |
|
chatglm.py
|
fix chatglm3 npu output (#11590)
|
2024-07-16 18:16:30 +08:00 |
|
chatglm4.py
|
support npu glm4 (#11539)
|
2024-07-09 15:46:49 +08:00 |
|
common.py
|
Add lm_head optimization on NPU (#11903)
|
2024-08-23 15:51:07 +08:00 |
|
convert.py
|
Initial NPU support for MiniCPM-V-2_6 (#11966)
|
2024-08-30 16:34:35 +08:00 |
|
convert_mp.py
|
Support lm_head of minicpm-2b on NPU (#12019)
|
2024-09-05 16:19:22 +08:00 |
|
kv.py
|
Initial NPU support for MiniCPM-V-2_6 (#11966)
|
2024-08-30 16:34:35 +08:00 |
|
linear.py
|
fix llama3-8b npu long input stuck (#11613)
|
2024-07-18 11:08:17 +08:00 |
|
llama.py
|
remove obselete npu code (#11967)
|
2024-08-29 14:16:44 -07:00 |
|
llama_mp.py
|
Optimize broadcast for npu llama (#12028)
|
2024-09-06 13:28:20 +08:00 |
|
minicpm.py
|
add minicpm 1B/2B npu support (#11507)
|
2024-07-04 16:31:04 +08:00 |
|
minicpm_mp.py
|
Support lm_head of minicpm-2b on NPU (#12019)
|
2024-09-05 16:19:22 +08:00 |
|
mistral.py
|
add mistral npu support (#11523)
|
2024-07-08 13:17:15 +08:00 |
|
mp_models_base.py
|
Support qwen2-1.5b with fused decoderlayer optimization on NPU (#11888)
|
2024-08-22 11:09:12 +08:00 |
|
phi3.py
|
add npu sdp (#11562)
|
2024-07-11 16:57:35 +08:00 |
|
phi3_v.py
|
optimize phi3-v encoder npu performance and add multimodal example (#11553)
|
2024-07-11 13:59:14 +08:00 |
|
qwen2.py
|
add qwen2 npu support (#11504)
|
2024-07-04 11:01:25 +08:00 |
|
qwen2_mp.py
|
Add input padding during prefill for qwen2-7b (#12033)
|
2024-09-06 16:39:59 +08:00 |
|
stablelm.py
|
Optimize stablelm on NPU (#11512)
|
2024-07-05 14:21:57 +08:00 |
