-
Notifications
You must be signed in to change notification settings - Fork 204
Insights: intel/intel-extension-for-transformers
Overview
-
- 3 Merged pull requests
- 2 Open pull requests
- 0 Closed issues
- 2 New issues
Loading
Could not load contribution data
Please try again later
Loading
3 Pull requests merged by 3 people
-
h2o for kv cache compression
#1468 merged
Jul 29, 2024 -
Update publication.md
#1677 merged
Jul 25, 2024 -
Adapt INC autoround changes
#1669 merged
Jul 25, 2024
2 Pull requests opened by 1 person
-
Bump torch from 1.13.1 to 2.2.0 in /workflows/compression_aware_training
#1679 opened
Jul 25, 2024
2 Issues opened by 2 people
-
AutoModelForCausalLM model.generate Wrong response by docker run the same chatglm3-int4 model bin file
#1680 opened
Jul 28, 2024 -
evaluation Parameter Parsing problem
#1676 opened
Jul 24, 2024
2 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.
-
ImportError: cannot import name 'WeightOnlyQuantizedLinear' from 'intel_extension_for_pytorch.nn.utils._quantize_convert'
#1630 commented on
Jul 25, 2024 • 0 new comments -
Adapt quant lm head
#1671 commented on
Jul 25, 2024 • 0 new comments