jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Update vLLM parameter max-seq-len-to-capture (#1809)

Browse Source 
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
This commit is contained in:
Liang Lv
2025-04-15 14:27:12 +08:00
committed by GitHub
parent a222d1cfbb
commit 13dd27e6d5
15 changed files with 15 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
AudioQnA/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -62,7 +62,7 @@ services:
cap_add:
- SYS_NICE
ipc: host
command: --model ${LLM_MODEL_ID} --tensor-parallel-size ${NUM_CARDS} --host 0.0.0.0 --port 80 --block-size ${BLOCK_SIZE} --max-num-seqs ${MAX_NUM_SEQS} --max-seq_len-to-capture ${MAX_SEQ_LEN_TO_CAPTURE}
command: --model ${LLM_MODEL_ID} --tensor-parallel-size ${NUM_CARDS} --host 0.0.0.0 --port 80 --block-size ${BLOCK_SIZE} --max-num-seqs ${MAX_NUM_SEQS} --max-seq-len-to-capture ${MAX_SEQ_LEN_TO_CAPTURE}
audioqna-gaudi-backend-server:
image: ${REGISTRY:-opea}/audioqna:${TAG:-latest}
container_name: audioqna-gaudi-backend-server

2
AudioQnA/kubernetes/helm/gaudi-values.yaml
View File

@@ -21,7 +21,7 @@ vllm:
"--tensor-parallel-size", "1",
"--block-size", "128",
"--max-num-seqs", "256",
"--max-seq_len-to-capture", "2048"
"--max-seq-len-to-capture", "2048"
]
whisper: