Changed KV type to fp8 in qwen3-coder-next recipe and reduced default context size to 131072 to ensure it all fits in a single Spark.

README.md

@@ -164,7 +164,7 @@ Don't do it every time you rebuild, because it will slow down compilation times.
 
 For periodic maintenance, I recommend using a filter: `docker builder prune --filter until=72h`
 
-### 2026-02-14
+### 2026-02-17
 
 #### Non-Privileged Mode Support
 
@@ -181,6 +181,8 @@ Example usage:
 ./launch-cluster.sh --non-privileged --mem-limit-gb 120 --shm-size-gb 64 exec vllm serve ...
 ```
 
+May result in a slightly reduced performance (within 2%) in exchange for better reliability and stability.
+
 ### 2026-02-12
 
 Added a mod for Qwen3-Coder-Next-FP8 that fixes:

recipes/qwen3-coder-next-fp8.yaml

@@ -24,7 +24,7 @@ defaults:
   host: 0.0.0.0
   tensor_parallel: 2
   gpu_memory_utilization: 0.7
-  max_model_len: 262144
+  max_model_len: 131072
 
 # Environment variables
 env: {}
@@ -37,6 +37,7 @@ command: |
     --gpu-memory-utilization {gpu_memory_utilization} \
     --host {host} \
     --port {port} \
+    --kv-cache-dtype fp8 \
     --load-format fastsafetensors \
     --attention-backend flashinfer \
     --enable-prefix-caching \