sirius/gcloud-lab
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update rtx6000-vllm.yaml

Browse source
This commit is contained in:
sirius0xdev 2026-05-02 09:11:46 -04:00 • committed by GitHub
parent 9a7904c219
commit 324c69faf9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 3 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml
View file

@ -39,8 +39,7 @@ spec:
- --tensor-parallel-size=1 - --tensor-parallel-size=1
- --tokenizer-mode=hf - --tokenizer-mode=hf
- --gpu-memory-utilization=0.95 - --gpu-memory-utilization=0.95
- --kv-cache-dtype=fp8 - --max-model-len=262144
- --max-model-len=256389
- --enable-auto-tool-choice - --enable-auto-tool-choice
- --enable-chunked-prefill - --enable-chunked-prefill
- --max-num-batched-tokens=8192 - --max-num-batched-tokens=8192
@ -48,9 +47,9 @@ spec:
- --trust-remote-code - --trust-remote-code
- --dtype=auto - --dtype=auto
- --enable-prefix-caching - --enable-prefix-caching
- --tool-call-parser=qwen3_coder - --tool-call-parser=qwen3_xml
- --reasoning-parser=qwen3 - --reasoning-parser=qwen3
- --disable-custom-all-reduce
ports: ports:
- containerPort: 8000 - containerPort: 8000
resources: resources: