diff --git a/static/js/cookbook.js b/static/js/cookbook.js
index d4f264e..33e2e10 100644
--- a/static/js/cookbook.js
+++ b/static/js/cookbook.js
@@ -366,6 +366,8 @@ export function _buildServeCmd(f, modelName, backend) {
     cmd += ` --gpu-memory-utilization ${f.gpu_mem || '0.90'}`;
     if (f.swap && f.swap !== '0') cmd += ` --swap-space ${f.swap}`;
     cmd += ` --dtype ${f.dtype || 'auto'}`;
+    const _kv = (f.vllm_kv_cache_dtype ?? '').toString().trim();
+    if (_kv === 'fp8') cmd += ' --kv-cache-dtype fp8';
     if (f.max_seqs && f.max_seqs.toString().trim()) cmd += ` --max-num-seqs ${f.max_seqs.toString().trim()}`;
     if (f.enforce_eager) cmd += ' --enforce-eager';
     if (f.trust_remote) cmd += ' --trust-remote-code';
diff --git a/static/js/cookbookRunning.js b/static/js/cookbookRunning.js
index 7cab3c7..ac27335 100644
--- a/static/js/cookbookRunning.js
+++ b/static/js/cookbookRunning.js
@@ -1332,6 +1332,7 @@ function _parseServeCmdToFields(cmd) {
     gpu_mem: ex(/--gpu-memory-utilization\s+([\d.]+)/) || '0.90',
     swap: ex(/--swap-space\s+(\d+)/) || '',
     dtype: ex(/--dtype\s+(\w+)/) || 'auto',
+    vllm_kv_cache_dtype: ex(/--kv-cache-dtype\s+([\w.-]+)/) || 'auto',
     max_seqs: ex(/--max-num-seqs\s+(\d+)/) || '',
     gpus: ex(/CUDA_VISIBLE_DEVICES=(\S+)/) || '',
     cache_type: ex(/(?:--cache-type-k|-ctk)\s+(\S+)/) || '',
diff --git a/static/js/cookbookServe.js b/static/js/cookbookServe.js
index b8db61b..666d947 100644
--- a/static/js/cookbookServe.js
+++ b/static/js/cookbookServe.js
@@ -453,6 +453,7 @@ function _rerenderCachedModels() {
           : (_es.gpus || detectedGpuIds));
       const tpOpts = [1,2,4,8].map(n => `<option${defaultTp==String(n)?' selected':''}>${n}</option>`).join('');
       const dtypeOpts = ['auto','float16','bfloat16'].map(d => `<option value="${d}"${sv('dtype','auto')===d?' selected':''}>${d}</option>`).join('');
+      const vllmKvCacheOpts = ['auto','fp8'].map(d => `<option value="${d}"${sv('vllm_kv_cache_dtype','auto')===d?' selected':''}>${d}</option>`).join('');
       const _l = (name, tip) => `<span>${name}<span class="hwfit-hint" title="${tip}">?</span></span>`;
       const _ggufChoices = _runnableGgufFiles(m);
       const _savedGguf = String(sv('gguf_file', '') || '');
@@ -524,6 +525,7 @@ function _rerenderCachedModels() {
       panelHtml += `<label class="hwfit-backend-vllm">${_l('Swap','CPU swap space in GB. Leave empty to omit (removed in newer vLLM)')}<input type="text" class="hwfit-sf" data-field="swap" value="${esc(sv('swap', ''))}" placeholder="off" /></label>`;
       panelHtml += `<label class="hwfit-backend-vllm hwfit-backend-sglang">${_l('Max Seqs','Maximum concurrent requests. Lower = less memory. Default 8 — prosumer GPUs often OOM on vLLM default 256 during CUDA graph capture.')}<input type="text" class="hwfit-sf" data-field="max_seqs" value="${esc(sv('max_seqs', '8'))}" placeholder="8" /></label>`;
       panelHtml += `<label>${_l('Dtype','Data type for weights. auto picks best for GPU')}<select class="hwfit-sf" data-field="dtype">${dtypeOpts}</select></label>`;
+      panelHtml += `<label class="hwfit-backend-vllm">${_l('KV Cache','vLLM --kv-cache-dtype. auto uses the model/runtime default; fp8 reduces KV memory for long context.')}<select class="hwfit-sf" data-field="vllm_kv_cache_dtype">${vllmKvCacheOpts}</select></label>`;
       panelHtml += `</div>`;
       // Row 2b: Diffusers settings
       const diffDtypeOpts = ['bfloat16','float16','float32'].map(d => `<option value="${d}"${sv('diff_dtype','bfloat16')===d?' selected':''}>${d}</option>`).join('');
@@ -882,6 +884,7 @@ function _rerenderCachedModels() {
             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+)/) || '',
             cache_type: _ex(/(?:--cache-type-k|-ctk)\s+(\S+)/) || '',
             llama_fit: _ex(/(?:--fit|-fit)\s+(on|off)/) || '',
diff --git a/tests/test_cookbook_helpers.py b/tests/test_cookbook_helpers.py
index b52fb00..cd7c980 100644
--- a/tests/test_cookbook_helpers.py
+++ b/tests/test_cookbook_helpers.py
@@ -257,6 +257,16 @@ def test_serve_runner_preserves_command_exit_code():
     assert 'echo "=== Process exited with code $? ==="' not in script
 
 
+def test_validate_serve_cmd_accepts_vllm_kv_cache_dtype():
+    cmd = (
+        "CUDA_VISIBLE_DEVICES=0,1 vllm serve nvidia/Qwen3.6-35B-A3B-NVFP4 "
+        "--host 0.0.0.0 --port 8000 --tensor-parallel-size 2 "
+        "--max-model-len 4096 --dtype auto --kv-cache-dtype fp8"
+    )
+
+    assert _validate_serve_cmd(cmd) == cmd
+
+
 def test_validate_serve_cmd_accepts_llama_advanced_controls():
     cmd = (
         "MODEL_FILE=$(printf %s ${HOME}'/.cache/huggingface/hub/models--Qwen--Qwen3-GGUF/snapshots/model.gguf') "