Commit graph

23 commits

Author SHA1 Message Date
Yishuo Wang
170e3d65e0
use new sdp and fp32 sdp (#11007) 2024-05-14 14:29:18 +08:00
Yishuo Wang
ad96f32ce0
optimize phi3 1st token performance (#10981) 2024-05-10 17:33:46 +08:00
Yishuo Wang
e753125880
use fp16_sdp when head_dim=96 (#10976) 2024-05-09 17:02:59 +08:00
Cengguang Zhang
75dbf240ec
LLM: update split tensor conditions. (#10872)
* LLM: update split tensor condition.

* add cond for split tensor.

* update priority of env.

* fix style.

* update env name.
2024-04-30 17:07:21 +08:00
Yishuo Wang
d884c62dc4
remove new_layout parameter (#10906) 2024-04-29 10:31:50 +08:00
Yishuo Wang
46ba962168
use new quantize kv (#10888) 2024-04-26 14:42:17 +08:00
Yina Chen
8811f268ff
Use new fp16 sdp in Qwen and modify the constraint (#10882) 2024-04-25 19:23:37 +08:00
Yina Chen
dc27b3bc35
Use sdp when rest token seq_len > 1 in llama & mistral (for lookup & spec) (#10790)
* update sdp condition

* update

* fix

* update & test llama

* mistral

* fix style

* update

* fix style

* remove pvc constrain

* update ds on arc

* fix style
2024-04-24 17:24:01 +08:00
Yishuo Wang
2d210817ff
add phi3 optimization (#10871) 2024-04-24 15:17:40 +08:00
Wang, Jian4
209c3501e6
LLM: Optimize qwen1.5 moe model (#10706)
* update moe block

* fix style

* enable optmize MLP

* enabel kv_cache

* enable fuse rope

* enable fused qkv

* enable flash_attention

* error sdp quantize

* use old api

* use fuse

* use xetla

* fix python style

* update moe_blocks num

* fix output error

* add cpu sdpa

* update

* update

* update
2024-04-18 14:54:05 +08:00
Xin Qiu
e764f9b1b1
Disable fast fused rope on UHD (#10780)
* use decoding fast path

* update

* update

* cleanup
2024-04-18 10:03:53 +08:00
Yishuo Wang
8f45e22072
fix llama2 (#10710) 2024-04-09 17:28:37 +08:00
Xin Qiu
3a9ab8f1ae
fix stablelm logits diff (#10636)
* fix logits diff

* Small fixes

---------

Co-authored-by: Yuwen Hu <yuwen.hu@intel.com>
2024-04-03 15:08:12 +08:00
binbin Deng
2bbd8a1548
LLM: fix llama2 FP16 & bs>1 & autotp on PVC and ARC (#10611) 2024-04-03 09:28:04 +08:00
Yuwen Hu
fd384ddfb8
Optimize StableLM (#10619)
* Initial commit for stablelm optimizations

* Small style fix

* add dependency

* Add mlp optimizations

* Small fix

* add attention forward

* Remove quantize kv for now as head_dim=80

* Add merged qkv

* fix lisence

* Python style fix

---------

Co-authored-by: qiuxin2012 <qiuxin2012cs@gmail.com>
2024-04-02 18:58:38 +08:00
Shaojun Liu
a10f5a1b8d
add python style check (#10620)
* add python style check

* fix style checks

* update runner

* add ipex-llm-finetune-qlora-cpu-k8s to manually_build workflow

* update tag to 2.1.0-SNAPSHOT
2024-04-02 16:17:56 +08:00
Cengguang Zhang
58b57177e3
LLM: support bigdl quantize kv cache env and add warning. (#10623)
* LLM: support bigdl quantize kv cache env and add warnning.

* fix style.

* fix comments.
2024-04-02 15:41:08 +08:00
Cengguang Zhang
e567956121
LLM: add memory optimization for llama. (#10592)
* add initial memory optimization.

* fix logic.

* fix logic,

* remove env var check in mlp split.
2024-04-02 09:07:50 +08:00
Qiyuan Gong
f4537798c1
Enable kv cache quantization by default for flex when 1 < batch <= 8 (#10584)
* Enable kv cache quantization by default for flex when 1 < batch <= 8.
* Change up bound from <8 to <=8.
2024-03-29 09:43:42 +08:00
Cengguang Zhang
b44f7adbad
LLM: Disable esimd sdp for PVC GPU when batch size>1 (#10579)
* llm: disable esimd sdp for pvc bz>1.

* fix logic.

* fix: avoid call get device name twice.
2024-03-28 22:55:48 +08:00
Ruonan Wang
ea4bc450c4
LLM: add esimd sdp for pvc (#10543)
* add esimd sdp for pvc

* update

* fix

* fix batch
2024-03-26 19:04:40 +08:00
Xin Qiu
1dd40b429c
enable fp4 fused mlp and qkv (#10531)
* enable fp4 fused mlp and qkv

* update qwen

* update qwen2
2024-03-26 08:34:00 +08:00
Wang, Jian4
9df70d95eb
Refactor bigdl.llm to ipex_llm (#24)
* Rename bigdl/llm to ipex_llm

* rm python/llm/src/bigdl

* from bigdl.llm to from ipex_llm
2024-03-22 15:41:21 +08:00
Renamed from python/llm/src/bigdl/llm/transformers/models/utils.py (Browse further)