software-engineering/edge-gitops
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix list

Browse Source
This commit is contained in:
HaimKortovich
2026-05-11 11:32:56 -05:00
parent 9594d6311a
commit 855cce3c54
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
clusters/k3s-dgx/nim-service/qwen.yaml
View File

@@ -63,8 +63,8 @@ spec:
- "131072" # ↑ 32K→128K — larger decode batches = more tokens/sec - "131072" # ↑ 32K→128K — larger decode batches = more tokens/sec
- --max-num-seqs - --max-num-seqs
- "254" # ↑ Allow more concurrent sequences - "254" # ↑ Allow more concurrent sequences
--enable-prefix-caching - --enable-prefix-caching
--dtype - --dtype
- "float8" # Explicit FP8 encoding - "float8" # Explicit FP8 encoding
--quantization --quantization
- "fbgemm-fp8" # Explicit quantization backend - "fbgemm-fp8" # Explicit quantization backend