Skip to content

Issues: PygmalionAI/aphrodite-engine

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

34 Open 61 Closed
34 Open 61 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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

[Bug]: Cannot load llama-3 gguf based models bug Something isn't working
#473 opened May 18, 2024 by EugeoSynthesisThirtyTwo
1
[Bug]: torch._dynamo.exc.BackendCompilerFailed with command-r-plus bug Something isn't working
#472 opened May 17, 2024 by heungson
[Bug]: Cannot load 70b exl2 5bpw model across 4 GPUs. bug Something isn't working
#471 opened May 14, 2024 by Ph0rk0z
7
[Bug]: Flash attention cannot be used on v0.5.3 bug Something isn't working
#468 opened May 12, 2024 by Nero10578
6
[Feature]: Exllamav2 Q4 cache
#463 opened May 9, 2024 by Anthonyg5005
2
[Bug]: LoRA broken when TP>1 bug Something isn't working
#460 opened May 8, 2024 by kubernetes-bad
[Usage]: Please provide the environment variable that closes the KoboldAI Lite page.
#445 opened Apr 30, 2024 by online2311
[Bug]: bug Something isn't working
#435 opened Apr 26, 2024 by someoneexistsontheinternet
@AlpinDale
1
[Feature]: Provide configuration via env vars or a configuration file
#425 opened Apr 22, 2024 by alexandreteles
@AlpinDale
[Feature]: Support hqq quantize method.
#418 opened Apr 17, 2024 by Minami-su
[Bug]: gguf loading failed. config.json? bug Something isn't working
#417 opened Apr 17, 2024 by juud79
4
[Feature]: Is there a reason CUDA 6.1 is the minimum? Would CUDA 6.0 on the P100 not work?
#413 opened Apr 16, 2024 by Nero10578
1
5
[Bug]: Converting gguf to state_dict bug Something isn't working
#411 opened Apr 16, 2024 by heungson
9
[Crash]: Program gets terminated
#401 opened Apr 11, 2024 by DuckY-Y
1
[Bug]: served-model-name is unused bug Something isn't working
#399 opened Apr 10, 2024 by mrseeker
1
[Feature]: any workarounds for cc 6.0?
#392 opened Apr 7, 2024 by Fuckingnameless
2
[Bug]: KV Cache and Max Tokens - Lack of Consistency bug Something isn't working
#362 opened Mar 28, 2024 by official-elinas
[Usage]: load-in-4bit not load after converted, and it seem not use swap well
#361 opened Mar 27, 2024 by yamosin
[Bug]: WSL Cuda out of Memory when Trying to Load GGUF Model bug Something isn't working
#360 opened Mar 26, 2024 by Lirikana
8
[Bug]: multi GPU crashes backend bug Something isn't working
#359 opened Mar 25, 2024 by mrseeker
6
[Feature]: BurstAttention: An Efficient Distributed Attention Framework for Extremely Long Sequences
#354 opened Mar 23, 2024 by sorasoras
1
[Bug]: Outlines json guided decoding bug Something isn't working
#353 opened Mar 22, 2024 by puppetm4st3r
2
[Misc]: Building docker container requires insane amount of memory
#350 opened Mar 21, 2024 by mrseeker
7
[Bug]: loading model with int8 kv cache chokes bug Something isn't working
#346 opened Mar 19, 2024 by BlairSadewitz
1
[Bug]: Issue when trying to load a AWQ model with --load-in-4bits for mixtral flavors bug Something isn't working
#342 opened Mar 19, 2024 by puppetm4st3r
9
ProTip! Adding no:label will show everything without a label.