@adelie/gpu-model-serving 0.6.3 → 0.6.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/package.json +1 -1
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@adelie/gpu-model-serving",
|
|
3
|
-
"version": "0.6.
|
|
3
|
+
"version": "0.6.5",
|
|
4
4
|
"description": "Stand up an OpenAI-compatible LLM endpoint on a rented or owned GPU box: pick the instance, fetch and quantize weights, serve with SGLang — speculative decoding, prefix caching and tool calling for agent workloads — then verify it and expose the port.",
|
|
5
5
|
"license": "Apache-2.0",
|
|
6
6
|
"repository": {
|