forked from huggingface/text-generation-inference
-
Notifications
You must be signed in to change notification settings - Fork 35
Insights: huggingface/tgi-gaudi
Overview
-
- 0 Merged pull requests
- 2 Open pull requests
- 0 Closed issues
- 3 New issues
There hasn’t been any commit activity on huggingface/tgi-gaudi in the last week.
Want to help out?
2 Pull requests opened by 2 people
-
Add support for Llava-next
#193 opened
Jul 24, 2024 -
[Torch compile ] Removed redundant and crashing changes
#194 opened
Jul 24, 2024
3 Issues opened by 3 people
-
Integration of llama3.1 fixes
#197 opened
Jul 29, 2024 -
Best Performance for a single card for Llama-2-7b-chat-hf
#196 opened
Jul 29, 2024 -
setting token flags still results in console warning
#195 opened
Jul 28, 2024
7 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.
-
Enable quantization with INC
#188 commented on
Jul 26, 2024 • 5 new comments -
adaptive batching
#192 commented on
Jul 26, 2024 • 4 new comments -
Unsupported model type llava_next
#186 commented on
Jul 24, 2024 • 0 new comments -
Misleading documentation
#174 commented on
Jul 28, 2024 • 0 new comments -
[Proposal]Perplexity metric addition for causallm
#169 commented on
Jul 29, 2024 • 0 new comments -
Driver compatibility check and document fixes
#182 commented on
Jul 30, 2024 • 0 new comments -
upgrade the tgi to V2.0.4
#187 commented on
Jul 31, 2024 • 0 new comments