-
### Feature Request
In order to do in-depth performance testing and monitoring of the cpptools extension we need to build some cross-plat automation and tooling to bring the data together
-
### Describe the bug
Can't load Mistral-Nemo-Instruct-2407, `Insufficient VRAM for model and cache`
This model size is 12B and my GPU memory is 120G.
### Is there an existing issue for this?
- [X]…
-
Calling `DLB_TALP_Attach()` from outside calls `shmem_cpuinfo_ext__init()` and `shmem_procinfo_ext__init()`. They both call `open_shmem()` -> `shmem_init()` -> `shm_open()`+ `ftruncate()`. This create…
-
Setting a high db pool size causes various sql query errors, most notably logins failing entirely. To fix it, shared memory for postgres needs to be increased with the following line in docker-compose…
-
Just to check my prerequisites, I've already read through https://github.com/mattn/go-sqlite3/issues/1205 and [the faq](https://github.com/mattn/go-sqlite3?tab=readme-ov-file#faq) so I'm pretty sure I…
-
Hello, we are facing an issue described at https://github.com/apache/apisix/issues/7349. Please advise on how to add the nginx parameter during deployment via the Helm chart:
```
http:
lua_shar…
-
Hello, I encountered an error of `Error 137` (see log output below). Do you have any insights what might cause the issue? Thanks!
```
...
Processed 70000000 kmers.
Processed 70100000 kmers.
Pro…
-
Regarding https://github.com/openjournals/joss-reviews/issues/7018 "State of the field: Do the authors describe how this software compares to other commonly-used packages?"
The paper does not seem …
-
**Description**
it complains OOM because it always executes on GPU0
name: "vllm1"
backend: "vllm"
# The usage of device is deferred to the vLLM engine
instance_group [
{
count: 1
k…
-
Implement shared memory counter to know how many processes are requesting a lock on the named semaphore.