Skip to content

Issues: microsoft/DeepSpeed-MII

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

196 Open 117 Closed
196 Open 117 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

ValueError: Unsupported model type mllama
#549 opened Dec 1, 2024 by MaorSagi
persistent deployment (qwen2-7b-instruct) model responds abnormally
#548 opened Nov 26, 2024 by chengjixin
splitting models across nodes
#547 opened Nov 26, 2024 by rastinrastinii
How to use data parallelism in multi gpus inference
#546 opened Nov 22, 2024 by hhf-hu
Issue: Multi-node and Multi-GPU Inference Problems with DeepSpeed MII
#545 opened Nov 20, 2024 by lcnmzz00
Please clarify structured output support
#544 opened Nov 19, 2024 by MRYingLEE
Bug: Removal of mii.pydantic_v1 broke entrypoint scripts
#543 opened Nov 11, 2024 by KMouratidis
@loadams
3
Updating transformers issue with bloom models
#541 opened Nov 1, 2024 by loadams
@loadams
Updating transformers issue with zero-shot-image-classification
#540 opened Nov 1, 2024 by loadams
@loadams
Logits Processors
#532 opened Oct 21, 2024 by psitronic
need help understanding profiler in deespeed mio
#531 opened Oct 7, 2024 by krishnanpooja
DeepSpeed with Phi-3-mini-128K-instruct does not generate <|endoftext|> token
#529 opened Sep 27, 2024 by shubhanshu786
@loadams
1
Repeated token generation with Phi-3-mini for longer context
#528 opened Sep 27, 2024 by shubhanshu786
LoRA Support
#527 opened Sep 27, 2024 by bagelbig
deepspeed MoE all_to_all communication
#526 opened Sep 19, 2024 by miaomiaoma0703
multi model deployment
#525 opened Sep 13, 2024 by whcjb
1
Question About Offloading and Recomputation
#523 opened Sep 9, 2024 by lxnlxnlxnlxnlxn
Configuration setting to pass parameters to tokenizer while encoding and decoding
#522 opened Aug 29, 2024 by krishnanpooja
OpenAI server fails
#521 opened Aug 24, 2024 by nivibilla
1
By default does deepspeed mii use bf16 dtype or fp16?
#518 opened Aug 21, 2024 by krishnanpooja
FileExistsError: [Errno 17] File exists: '/tmp/mii_cache' ` on generate function call
#516 opened Aug 6, 2024 by krishnanpooja
non-persistent example doesn't work on Mixtral-8*7B-v0.1
#513 opened Jul 26, 2024 by tang-t21
non-persistent simple example does not work
#506 opened Jul 16, 2024 by mohbay
@loadams
5
Dummy data loading?
#505 opened Jul 14, 2024 by guqiqi
Client cannot find deployment error
#504 opened Jul 12, 2024 by heiseon
ProTip! Type g i on any issue or pull request to go back to the issue listing page.