Skip to content

Issues: HabanaAI/vllm-fork

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

20 Open 26 Closed
20 Open 26 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

[Bug]: TypeError: FusedSDPA.forward() takes from 4 to 9 positional arguments but 12 were given bug Something isn't working
#462 opened Nov 6, 2024 by Zhenzhong1
1 task done
[Usage]: How to run FP8 inference
#453 opened Nov 3, 2024 by warlock135
1 task done
1
[Installation]: v0.5.3.post1+Gaudi-1.18.0 has unknown manifest with 2.4.1 pytorch image
#450 opened Oct 31, 2024 by vbedida79
1 task done
[Bug]: the generated text on BFloat16 is not as good as that on Float32. bug Something isn't working
#443 opened Oct 29, 2024 by ccrhx4
1 task done
@madamczykhabana
1
[Bug]: Engine loop has died bug Something isn't working
#419 opened Oct 23, 2024 by warlock135
1 task done
7
[Bug]: MQLLMEngine dies after a period of inactivity bug Something isn't working
#416 opened Oct 23, 2024 by Xaenalt
1 task done
2
[Feature][habana-main]: HPUAttentionImpl support for 'Encoder_Decoder'
#370 opened Oct 7, 2024 by xuechendi
1 task done
[RFC]: change VLLM_DECODE_BLOCK_BUCKET_* design to fit small AND large batch size at one warmup intel Issues or PRs submitted by Intel
#328 opened Sep 24, 2024 by ccrhx4
1 task done
2
[Bug]: 10% perf drop on mixtral8x22b due to commit b62fba85ac03326e9f466d8d37e91ae1b14a6511 bug Something isn't working
#305 opened Sep 20, 2024 by hlin99
4
[Bug]: block_softmax accuracy issue in flat_pa kernel, qwen2-7B model bug Something isn't working
#275 opened Sep 12, 2024 by jikunshang
@madamczykhabana
44
[Usage]: The TP improvement is not as expectation
#274 opened Sep 12, 2024 by JunxiChhen
1
[Bug]: Using tensor parallel during offline inference causes the process to hang bug Something isn't working
#220 opened Aug 30, 2024 by xinsu626
2
[Misc]: issue with loading weights from safetensors files external Issues or PRs submitted by external users
#211 opened Aug 28, 2024 by huijjj
4
[Usage]: The prompt bucket shape will not impact the performance intel Issues or PRs submitted by Intel
#209 opened Aug 28, 2024 by JunxiChhen
[Feature]: support pipeline parallelism inference in vllm intel Issues or PRs submitted by Intel
#205 opened Aug 27, 2024 by Zjq9409
2
[Usage]: tensor-parallel-size=2 second token latency is higher than tensor_parallel_size=1 intel Issues or PRs submitted by Intel
#204 opened Aug 26, 2024 by Zjq9409
[Feature]: Compile warmup take too long intel Issues or PRs submitted by Intel
#201 opened Aug 26, 2024 by Zjq9409
1
[Bug]: benchmark_latency.py cannot exit when using tp bug Something isn't working intel Issues or PRs submitted by Intel
#197 opened Aug 21, 2024 by JunxiChhen
4
[Usage]: vllm can't run qwen 32B inference external Issues or PRs submitted by external users
#193 opened Aug 17, 2024 by kunger97
@afierka-intel
4
[Bug]: Device type HPU is not supported for torch.Generator() api bug Something isn't working habana Issues or PRs submitted by Habana Labs
#183 opened Aug 14, 2024 by sungwook-son
2
ProTip! Mix and match filters to narrow down what you’re looking for.