xinfer-ai 0.12.3 → 0.12.5
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/README.md +1 -0
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -446,6 +446,7 @@ Constraint-based generation via llguidance — Lark grammars, regex, JSON Schema
|
|
|
446
446
|
| `--pd-url` | PD connection URL (`tcp://`, `http://`, `file://`) |
|
|
447
447
|
| `--disable-prefix-cache` | Disable prefix caching |
|
|
448
448
|
| `--prefix-cache-max-tokens` | Cap prefix cache size |
|
|
449
|
+
| `--prefill-chunk-size` | Cap prefill chunk size (default: CUDA 8K, Metal: 4k) |
|
|
449
450
|
| `--disable-cuda-graph` | Disable CUDA graph capture |
|
|
450
451
|
| `--yarn-scaling-factor` | YARN RoPE context extension factor |
|
|
451
452
|
| `--temperature` | Sampling temperature (0–1) |
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "xinfer-ai",
|
|
3
|
-
"version": "0.12.
|
|
4
|
-
"assetVersion": "0.12.
|
|
3
|
+
"version": "0.12.5",
|
|
4
|
+
"assetVersion": "0.12.5",
|
|
5
5
|
"description": "xInfer — a high-performance LLM inference engine in Rust with CUDA/Metal acceleration",
|
|
6
6
|
"license": "MIT",
|
|
7
7
|
"homepage": "https://github.com/guoqingbao/xinfer#readme",
|