feat: add vllm kv cache dtype option (#1185)

This commit is contained in:
spooky
2026-06-03 00:17:16 +10:00
committed by GitHub
parent 7b43fa9372
commit 5b87e69221
4 changed files with 16 additions and 0 deletions
+1
View File
@@ -1332,6 +1332,7 @@ function _parseServeCmdToFields(cmd) {
gpu_mem: ex(/--gpu-memory-utilization\s+([\d.]+)/) || '0.90',
swap: ex(/--swap-space\s+(\d+)/) || '',
dtype: ex(/--dtype\s+(\w+)/) || 'auto',
vllm_kv_cache_dtype: ex(/--kv-cache-dtype\s+([\w.-]+)/) || 'auto',
max_seqs: ex(/--max-num-seqs\s+(\d+)/) || '',
gpus: ex(/CUDA_VISIBLE_DEVICES=(\S+)/) || '',
cache_type: ex(/(?:--cache-type-k|-ctk)\s+(\S+)/) || '',