-
Notifications
You must be signed in to change notification settings - Fork 194
Insights: intel/intel-extension-for-transformers
Overview
-
- 13 Merged pull requests
- 5 Open pull requests
- 1 Closed issue
- 0 New issues
Could not load contribution data
Please try again later
13 Pull requests merged by 8 people
-
Improve SQ model restored from json
#1600 merged
Jun 11, 2024 -
Fix SQ baichuan without position_ids for torch and ipex 2.3.0
#1597 merged
Jun 11, 2024 -
catch prepack error and fallback to torch bf16
#1526 merged
Jun 7, 2024 -
[NeuralChat][UI]: updated side_by_side client
#1556 merged
Jun 7, 2024 -
Add a dependency for Neural_chat on CPU device
#1579 merged
Jun 7, 2024 -
Add text-gen finetune workflow for glue mnli
#1478 merged
Jun 7, 2024 -
requirements.txt for intel_extension_for_transformers/neural_chat/examples/helloworld
#1542 merged
Jun 7, 2024 -
[CI]Add model test on arc
#1583 merged
Jun 7, 2024 -
Unify the woq config weight_dtype for int4 and fp4 on different devices
#1594 merged
Jun 7, 2024 -
update qbits doc
#1599 merged
Jun 7, 2024 -
improve lm_eval get chatglm2 tokenizer from local saved files
#1598 merged
Jun 7, 2024 -
remove INC 1.X API usage in neuralchat doc
#1595 merged
Jun 6, 2024 -
improve SQ to adapt optimum-intel 1.16.1
#1591 merged
Jun 6, 2024
5 Pull requests opened by 4 people
-
Enable vllm backend.
#1602 opened
Jun 11, 2024 -
add publications
#1603 opened
Jun 11, 2024 -
[DOC] Update example doc
#1604 opened
Jun 12, 2024 -
Migrate trainer INC 1.x API to 2.x
#1605 opened
Jun 12, 2024 -
Migrate SQ and WOQ to INC 3.x API.
#1606 opened
Jun 12, 2024
1 Issue closed by 1 person
-
Can't load woq int4 model
#1104 closed
Jun 6, 2024
5 Unresolved conversations
Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.
-
Gaudi Tensor split for memory optimization
#1575 commented on
Jun 7, 2024 • 1 new comment -
Support huggingface popular weight format for weight-only quantization
#1580 commented on
Jun 7, 2024 • 1 new comment -
h2o for kv cache compression
#1468 commented on
Jun 11, 2024 • 0 new comments -
[DOC]Add modelscope example
#1578 commented on
Jun 11, 2024 • 0 new comments -
[NeuralChat] Refine path in AskDoc server
#1593 commented on
Jun 12, 2024 • 0 new comments