-
I have surveyed lots of projects using ps-lite to implement BSP model.
Most of them simply behave like:
```
kv.wait(kv.push)
kv.wait(kv.pull)
```
I do not think they are real BSP model because e…
-
"A link in markdown will always 404 if it does not exist instead of using the 301 redirects set up.
We should:
make tests to ensure these links always exist
OR
design it so that they 301 appro…
-
This issues describes the high level directions that "create LLM Engine V2". We want the design to be as transparent as possible and created this issue to track progress and solicit feedback.
Goal…
-
There are some APIs at Cloudflare that do not follow our common use of json for request and response bodies: Two examples of this:
1. Reading a Workers KV value by key returns a raw string body: http…
-
### What did you do?
1. 07:51 - 07:55 Create 4 CDC clusters (each CDC cluster with 32C CDC nodes), for each CDC cluster create one changefeed, each changefeed replicating ~40k tables (overall ~160k …
-
### System Info
- CPU: x86_64
- CPU mem: 64GB
- GPU name: V100 SXM2 16GB and Tesla T4 15GB both happens
- Libraries
- TensorRT-LLM commit https://github.com/NVIDIA/TensorRT-LLM/tree/3c46c2794e7f6df48…
-
please add a feature graphql caching in workers kv
-
scribbling just a few thoughts from a brainstorming session with @1000hz in Austin.
what if instead of:
```js
export default defineConfig({
plugins: [
cloudflare({
environments: {
w…
-
I think it is already listed in your internal TODOs, but just for sure. 😅
-
ATM the local KV instances are always backed by an SQLite database.
There would be at least two use-cases where having a memory only backend would be interesting:
- Memcached/Redis alternative, th…