-
Hi,
I am running a test with multiCapabilities, one in chrome and another in firefox. When I run the test, it successfully run the test parallely in Cross Browser mode. I am using Jasmine Framew…
-
### Issue Description
Syslog Errors ERR GenericConfigUpdater: 'apply-patch' executed failed for localhost while running generic_config_updater/test_ecn_config_update.py
### Results you see
…
-
The current benchmarking script if specified with `INF` arrivals, will not limit the maximum concurrency level as shown [here](https://github.com/vllm-project/vllm/blob/703e42ee4b3efed3c71e7ae7d15f0f9…
-
Currently, it is not possible to have concurrent battles. Although you can specify `max_concurrent_battles`, what it does (as far as I can tell) is spawn multiple battles but only allow you to call `c…
-
Hello, I'm very interested in your work. I train boxnet successfully with python 3.8 , torch 2.0.1 and cuda11.7. And then I want to finetune the unet, so I set '--train_unet' True and train on the sam…
-
# torchtolinalg pipeline issue
Related iree issues: https://github.com/iree-org/iree/issues/17021
The following two run should generate same issue, but it turns out not
## Run without --torchtolina…
-
Specifically it failed at dealing with DTensor `MaskPartial` placement of sharded embedding.
This only happens when we do whole model compile.
TransformerBlock-level compilation (default) + separa…
-
This issue will be used for discussion for the standard library. Questions include:
- How big should it be?
- How much do we care about performance vs ease of use
- How should it be packaged/where …
-
### Problem Description
I've encountered an issue when using the `LCSSMatcher.match_trace_batch()` method for batch matching with multiprocessing. Below is the method definition for reference:
`…
-
### Your current environment
```text
The output of `python collect_env.py`
```
### 🐛 Describe the bug
command to start vllm:
```yaml
command: ["python3", "-m", "vllm.entrypoints.opena…