-
### Report of performance regression
Using your benchmark
```
git clone https://github.com/vllm-project/vllm
cd vllm/benchmarks
wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vi…
-
## Bug Report
Please answer these questions before submitting your issue. Thanks!
### 1. Minimal reproduce step (Required)
Apply this patch:
```diff
diff --git a/pkg/ddl/tests/partition…
-
### Problem
Wondering if basic support already exists.
Llama vision 3.2 is unlike https://github.com/turboderp/exllamav2/issues/399, and in some ways may be very easy for basic Exllama integration…
-
### Describe the bug
Having a grpc service which returns Multi and grpc client which is cancelled after some time, grpc service continue to produce items (looks similar to https://github.com/quarku…
-
Hello there,
I am learning to use DEAP library to perform multi-objective optimization, I am largely fitting my problem based on the example shown in this [link](https://github.com/lmarti/evolution…
-
(kwav2vec_env_py3_8) root@4aa7addb6281:/home# bash script/inference/evaluate_multimodel.sh
INFO:__main__:Namespace(add_weight=0.5, additional_output=False, autoregressive=False, batch_size=8, batch_s…
-
I have a Diffuser that used to work with the other Tuya contrib, but i don't get a connection anymore. With this contrib it works, but I am not able to use my previous commands. ![image](https://githu…
-
## Bug Report
Please answer these questions before submitting your issue. Thanks!
### 1. Minimal reproduce step (Required)
```
CREATE TABLE `PK_MULTI_COL_4820` (
`COL1` binary(10) NOT N…
-
I have noticed that ollama always outputs content at a fixed speed, and most of the time, the GPU is not fully utilized(0% load), indicating that the bottleneck in generating content is not in the GPU…
-
### Describe the bug
Multi-line signatures have a comma separator even for the last parameter when outputting HTML5 (edit: and LaTeX and Text).
The offender seems to be [writers/html5.py#L232](h…