diff options
Diffstat (limited to 'snippets/hyperstack/hyperstack-vm.toml')
| -rw-r--r-- | snippets/hyperstack/hyperstack-vm.toml | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/snippets/hyperstack/hyperstack-vm.toml b/snippets/hyperstack/hyperstack-vm.toml index f1c80a7..4ec6879 100644 --- a/snippets/hyperstack/hyperstack-vm.toml +++ b/snippets/hyperstack/hyperstack-vm.toml @@ -100,7 +100,9 @@ container_name = "vllm_nemotron_super" max_model_len = 65536 gpu_memory_utilization = 0.92 tensor_parallel_size = 1 -tool_call_parser = "" +# llama3_json lets vLLM accept tool_choice requests (required by opencode). +# Nemotron won't spontaneously call tools, so the vLLM 0.17.1 token_ids bug won't trigger. +tool_call_parser = "llama3_json" trust_remote_code = true # OpenAI GPT-OSS 20B — ultra-fast MoE (3.6B active / 20B total, MXFP4), ~14 GB on A100. |