Skip to content

Issues: huggingface/text-generation-inference

Nightly load test results
#2235 opened Jul 15, 2024 by Hugoch
Open 2
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

98 Open 1,136 Closed
98 Open 1,136 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

local installation fail
#2322 opened Jul 28, 2024 by ragesh2000
2 of 4 tasks
4
Feature request: Add documentation and examples for adding additional API endpoints.
#2321 opened Jul 27, 2024 by michael-conrad
1
Possible config mismatch between TGI and transformers (hidden_act vs. hidden_activation)
#2319 opened Jul 26, 2024 by xenova
4 tasks
1
Regex response type is not respected
#2318 opened Jul 26, 2024 by aymeric-roucher
2
Request failed during generation: Server error: Batch ID 408 not found in cache.
#2316 opened Jul 26, 2024 by leizhao1234
5
LLama 3/3.1 70B Outputting "!!!!!!"; Shorter Context
#2312 opened Jul 26, 2024 by mallorbc
2 of 4 tasks
4
Tools still giving EoF errors on generated JSON
#2310 opened Jul 25, 2024 by ArjunBhalla98
1 of 4 tasks
@drbh
how to use the model's checkpoint in local fold?
#2302 opened Jul 25, 2024 by zk19971101
1 of 4 tasks
1
Can't run llama3.1-70b at full context
#2301 opened Jul 24, 2024 by pseudotensor
2 of 4 tasks
9
AttributeError: 'NoneType' object has no attribute 'replace'
#2297 opened Jul 24, 2024 by almersawi
2 of 4 tasks
1
1
FinishReason enum not compatible with OAI api
#2296 opened Jul 24, 2024 by jondot
@drbh
3
paged attention in tgi is fake?
#2294 opened Jul 24, 2024 by CSEEduanyu
4 tasks
2
Meta-Llama-3.1-405B-Instruct-BNB-NF4 - Shard process was signaled to shutdown with signal 11
#2293 opened Jul 24, 2024 by BugsBuggy
1 of 4 tasks
@drbh
1
Server crashes when provided with invalid JSON schema
#2280 opened Jul 22, 2024 by npt
2 of 4 tasks
1
@drbh
2
Latest Docker image fails while initializing gemma2
#2275 opened Jul 22, 2024 by jorado
2 of 4 tasks
1
DeepSeek-Coder-V2-Lite-Instruct-AWQ
#2267 opened Jul 21, 2024 by Ichigo3766
1
gemma-7b warmup encountered an error
#2265 opened Jul 21, 2024 by Amanda-Barbara
2 of 4 tasks
2
Add support for Flash Attention 3 feature request New feature or request
#2264 opened Jul 20, 2024 by RonanKMcGovern
1
Documentation about default values of model paramaters
#2263 opened Jul 19, 2024 by mohittalele
2
TGI fails with local LORA adapters
#2253 opened Jul 19, 2024 by p-davidk
2 of 4 tasks
1
Add support for Mistral-Nemo new model Request for integration of new model
#2252 opened Jul 18, 2024 by shaltielshmid
2 tasks done
5
can't start server with small --max-total-tokens. But works fine with big stting question Further information is requested
#2246 opened Jul 18, 2024 by rooooc
4
max_batch_size limit doesn't work well at queue.next_batch()
#2241 opened Jul 17, 2024 by AndersWXJY
2
tool_calls gives sporadic EoF parsing errors
#2240 opened Jul 16, 2024 by ArjunBhalla98
2 of 4 tasks
@drbh
4
Can I somehow change attention type from 'FlashAttention' in the text-server-launcher? question Further information is requested
#2239 opened Jul 16, 2024 by wasifmasood
1
ProTip! Exclude everything labeled bug with -label:bug.