Issues: ModelTC/lightllm
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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
[BUG] Slow Tokenizer Message is printing when the Fast Tokenizer may be in use
bug
Something isn't working
#407
opened May 7, 2024 by
david-vectorflow
[BUG] There already is a lightllm in pypi
bug
Something isn't working
#380
opened Mar 26, 2024 by
rlippmann
1 task
Qwen-14B-INT8 face the issue: 'QwenTransformerLayerWeight' object has no attribute 'q_weight_'
bug
Something isn't working
#333
opened Feb 20, 2024 by
wangr0031
Inconsistent Output between LightLLM and Transformers Inference Library
bug
Something isn't working
#309
opened Jan 19, 2024 by
Lvjinhong
Is there any comparison of the effects related to token attention? For example, compare with page attention
#268
opened Dec 27, 2023 by
skykiseki
[BUG] Qwen-7B-Chat AttributeError: 'LlamaSplitFuseInferStateInfo' object has no attribute 'logn_values'
bug
Something isn't working
#239
opened Dec 2, 2023 by
exceedzhang
1 task
no attribute 'qkv_weight_' AttributeError when load Qwen-14B-Chat-Int4
bug
Something isn't working
#234
opened Dec 1, 2023 by
jarviszeng-zjc
[BUG] Assertation error self.config["num_attention_heads"] % self.world_size_ == 0 when not perfectly divisible
bug
Something isn't working
#233
opened Nov 30, 2023 by
getorca
An error occurred while deploying the 4bit version of Yi-34B-Chat
#230
opened Nov 29, 2023 by
wx971025
[BUG] triton 2.0.0.dev20221202 has a memory leak bug, and fix way.
bug
Something isn't working
#209
opened Nov 13, 2023 by
hiworldwzj
高并发输出不稳定
bug
Something isn't working
enhancement
New feature or request
#203
opened Nov 10, 2023 by
GavinZhao19
Previous Next
ProTip!
What’s not been updated in a month: updated:<2024-04-13.