vllm - 💡(How to fix) Fix [Bug]: Dsv4-Flash blank `/v1/completions` response

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

Code Example

main 4140faa4a

---

vllm serve deepseek-ai/DeepSeek-V4-Flash \
  --enforce-eager \
  --block-size 256 \
  --gpu-memory-utilization 0.9 \
  --max-model-len 4096 \
  --trust-remote-code \
  --seed 42 \
  --data-parallel-size 4 \
  --tensor-parallel-size 1 \
  --enable-expert-parallel \
  --kv-cache-dtype fp8 \
  --no-enable-prefix-caching

---

(llmd) NickLucche@nma-frk-sa-h100-00-preserve ➜  llmd git:(master) ✗ just send_request2
curl -X POST http://localhost:$(just port 8194)/v1/completions -H "Content-Type: application/json" -d '{ "model": "deepseek-ai/DeepSeek-V4-Flash", "prompt": "Can you complete this latin sentence: Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.", "max_tokens": 150, "temperature": 0.0 }'
{"id":"cmpl-a11769f6174d63f9","object":"text_completion","created":1778253935,"prompt_routed_experts":null,"model":"deepseek-ai/DeepSeek-V4-Flash","choices":[{"index":0,"text":"","logprobs":null,"finish_reason":"stop","stop_reason":null,"token_ids":null,"prompt_logprobs":null,"prompt_token_ids":null,"routed_experts":null}],"service_tier":null,"system_fingerprint":"vllm-0.20.2rc1.dev140+g4140faa4a-dp4-ep-221f27d0","usage":{"prompt_tokens":125,"total_tokens":126,"completion_tokens":1,"prompt_tokens_details":null},"kv_transfer_params":null}%
(llmd) NickLucche@nma-frk-sa-h100-00-preserve ➜  llmd git:(master) ✗ just send_request2
curl -X POST http://localhost:$(just port 8194)/v1/completions -H "Content-Type: application/json" -d '{ "model": "deepseek-ai/DeepSeek-V4-Flash", "prompt": "Can you complete this latin sentence: Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.", "max_tokens": 150, "temperature": 0.0 }'
{"id":"cmpl-babf270348341bbc","object":"text_completion","created":1778253938,"prompt_routed_experts":null,"model":"deepseek-ai/DeepSeek-V4-Flash","choices":[{"index":0,"text":"","logprobs":null,"finish_reason":"stop","stop_reason":null,"token_ids":null,"prompt_logprobs":null,"prompt_token_ids":null,"routed_experts":null}],"service_tier":null,"system_fingerprint":"vllm-0.20.2rc1.dev140+g4140faa4a-dp4-ep-221f27d0","usage":{"prompt_tokens":125,"total_tokens":126,"completion_tokens":1,"prompt_tokens_details":null},"kv_transfer_params":null}%
(llmd) NickLucche@nma-frk-sa-h100-00-preserve ➜  llmd git:(master) ✗ just send_request2
curl -X POST http://localhost:$(just port 8194)/v1/completions -H "Content-Type: application/json" -d '{ "model": "deepseek-ai/DeepSeek-V4-Flash", "prompt": "Can you complete this latin sentence: Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.", "max_tokens": 150, "temperature": 0.0 }'
{"id":"cmpl-9c6f2b1941545af4","object":"text_completion","created":1778253946,"prompt_routed_experts":null,"model":"deepseek-ai/DeepSeek-V4-Flash","choices":[{"index":0,"text":"","logprobs":null,"finish_reason":"stop","stop_reason":null,"token_ids":null,"prompt_logprobs":null,"prompt_token_ids":null,"routed_experts":null}],"service_tier":null,"system_fingerprint":"vllm-0.20.2rc1.dev140+g4140faa4a-dp4-ep-221f27d0","usage":{"prompt_tokens":125,"total_tokens":126,"completion_tokens":1,"prompt_tokens_details":null},"kv_transfer_params":null}%
(llmd) NickLucche@nma-frk-sa-h100-00-preserve ➜  llmd git:(master) ✗ just send_request2
curl -X POST http://localhost:$(just port 8194)/v1/completions -H "Content-Type: application/json" -d '{ "model": "deepseek-ai/DeepSeek-V4-Flash", "prompt": "Can you complete this latin sentence: Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.", "max_tokens": 150, "temperature": 0.0 }'
{"id":"cmpl-a5b2d4e57ea77345","object":"text_completion","created":1778253950,"prompt_routed_experts":null,"model":"deepseek-ai/DeepSeek-V4-Flash","choices":[{"index":0,"text":"","logprobs":null,"finish_reason":"stop","stop_reason":null,"token_ids":null,"prompt_logprobs":null,"prompt_token_ids":null,"routed_experts":null}],"service_tier":null,"system_fingerprint":"vllm-0.20.2rc1.dev140+g4140faa4a-dp4-ep-221f27d0","usage":{"prompt_tokens":125,"total_tokens":126,"completion_tokens":1,"prompt_tokens_details":null},"kv_transfer_params":null}%
(llmd) NickLucche@nma-frk-sa-h100-00-preserve ➜  llmd git:(master) ✗ just send_request2
curl -X POST http://localhost:$(just port 8194)/v1/completions -H "Content-Type: application/json" -d '{ "model": "deepseek-ai/DeepSeek-V4-Flash", "prompt": "Can you complete this latin sentence: Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.", "max_tokens": 150, "temperature": 0.0 }'
{"id":"cmpl-ae1d1d42855c1cca","object":"text_completion","created":1778253952,"prompt_routed_experts":null,"model":"deepseek-ai/DeepSeek-V4-Flash","choices":[{"index":0,"text":"","logprobs":null,"finish_reason":"stop","stop_reason":null,"token_ids":null,"prompt_logprobs":null,"prompt_token_ids":null,"routed_experts":null}],"service_tier":null,"system_fingerprint":"vllm-0.20.2rc1.dev140+g4140faa4a-dp4-ep-221f27d0","usage":{"prompt_tokens":125,"total_tokens":126,"completion_tokens":1,"prompt_tokens_details":null},"kv_transfer_params":null}%
(llmd) NickLucche@nma-frk-sa-h100-00-preserve ➜  llmd git:(master) ✗ just send_request2
curl -X POST http://localhost:$(just port 8194)/v1/completions -H "Content-Type: application/json" -d '{ "model": "deepseek-ai/DeepSeek-V4-Flash", "prompt": "Can you complete this latin sentence: Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.", "max_tokens": 150, "temperature": 0.0 }'
{"id":"cmpl-97180f58b9d4d992","object":"text_completion","created":1778253953,"prompt_routed_experts":null,"model":"deepseek-ai/DeepSeek-V4-Flash","choices":[{"index":0,"text":"","logprobs":null,"finish_reason":"stop","stop_reason":null,"token_ids":null,"prompt_logprobs":null,"prompt_token_ids":null,"routed_experts":null}],"service_tier":null,"system_fingerprint":"vllm-0.20.2rc1.dev140+g4140faa4a-dp4-ep-221f27d0","usage":{"prompt_tokens":125,"total_tokens":126,"completion_tokens":1,"prompt_tokens_details":null},"kv_transfer_params":null}%
(llmd) NickLucche@nma-frk-sa-h100-00-preserve ➜  llmd git:(master) ✗ just send_request2
curl -X POST http://localhost:$(just port 8194)/v1/completions -H "Content-Type: application/json" -d '{ "model": "deepseek-ai/DeepSeek-V4-Flash", "prompt": "Can you complete this latin sentence: Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.", "max_tokens": 150, "temperature": 0.0 }'
{"id":"cmpl-a12ae05e1285ca20","object":"text_completion","created":1778253954,"prompt_routed_experts":null,"model":"deepseek-ai/DeepSeek-V4-Flash","choices":[{"index":0,"text":"","logprobs":null,"finish_reason":"stop","stop_reason":null,"token_ids":null,"prompt_logprobs":null,"prompt_token_ids":null,"routed_experts":null}],"service_tier":null,"system_fingerprint":"vllm-0.20.2rc1.dev140+g4140faa4a-dp4-ep-221f27d0","usage":{"prompt_tokens":125,"total_tokens":126,"completion_tokens":1,"prompt_tokens_details":null},"kv_transfer_params":null}%                                                                                                        (llmd) NickLucche@nma-frk-sa-h100-00-preserve ➜  llmd git:(master)
---

(llmd) NickLucche@nma-frk-sa-h100-00-preserve ➜  llmd git:(master) ✗ just send_request2
curl -X POST http://localhost:$(just port 8194)/v1/completions -H "Content-Type: application/json" -d '{ "model": "deepseek-ai/DeepSeek-V4-Flash", "prompt": "Can you complete this latin sentence: Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.", "max_tokens": 150, "temperature": 0.0 }'


{"id":"cmpl-ab1152b3bdfbaf04","object":"text_completion","created":1778254046,"prompt_routed_experts":null,"model":"deepseek-ai/DeepSeek-V4-Flash","choices":[{"index":0,"text":" Et harum quidem rerum facilis est et expedita distinctio. Nam libero tempore, cum soluta nobis est eligendi optio cumque nihil impedit quo minus id quod maxime placeat facere possimus, omnis voluptas assumenda est, omnis dolor repellendus. Temporibus autem quibusdam et aut officiis debitis aut rerum necessitatibus saepe eveniet ut et voluptates repudiandae sint et molestiae non recusandae. Itaque earum rerum hic tenetur a sapiente delectus, ut aut reiciendis voluptatibus maiores alias consequatur aut perferendis doloribus asperiores repellat. Lorem ipsum","logprobs":null,"finish_reason":"length","stop_reason":null,"token_ids":null,"prompt_logprobs":null,"prompt_token_ids":null,"routed_experts":null}],"service_tier":null,"system_fingerprint":"vllm-0.20.2rc1.dev140+g4140faa4a-dp4-ep-221f27d0","usage":{"prompt_tokens":125,"total_tokens":275,"completion_tokens":150,"prompt_tokens_details":null},"kv_transfer_params":null}%
RAW_BUFFERClick to expand / collapse

Your current environment

<details> <summary>The output of <code>python collect_env.py</code></summary>
main 4140faa4a
</details>

🐛 Describe the bug

Spin up a simple colocated deployment (H100)

vllm serve deepseek-ai/DeepSeek-V4-Flash \
  --enforce-eager \
  --block-size 256 \
  --gpu-memory-utilization 0.9 \
  --max-model-len 4096 \
  --trust-remote-code \
  --seed 42 \
  --data-parallel-size 4 \
  --tensor-parallel-size 1 \
  --enable-expert-parallel \
  --kv-cache-dtype fp8 \
  --no-enable-prefix-caching

I can observe the following behavior quite consistently, in which the model just produces no output

(llmd) NickLucche@nma-frk-sa-h100-00-preserve ➜  llmd git:(master) ✗ just send_request2
curl -X POST http://localhost:$(just port 8194)/v1/completions -H "Content-Type: application/json" -d '{ "model": "deepseek-ai/DeepSeek-V4-Flash", "prompt": "Can you complete this latin sentence: Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.", "max_tokens": 150, "temperature": 0.0 }'
{"id":"cmpl-a11769f6174d63f9","object":"text_completion","created":1778253935,"prompt_routed_experts":null,"model":"deepseek-ai/DeepSeek-V4-Flash","choices":[{"index":0,"text":"","logprobs":null,"finish_reason":"stop","stop_reason":null,"token_ids":null,"prompt_logprobs":null,"prompt_token_ids":null,"routed_experts":null}],"service_tier":null,"system_fingerprint":"vllm-0.20.2rc1.dev140+g4140faa4a-dp4-ep-221f27d0","usage":{"prompt_tokens":125,"total_tokens":126,"completion_tokens":1,"prompt_tokens_details":null},"kv_transfer_params":null}%
(llmd) NickLucche@nma-frk-sa-h100-00-preserve ➜  llmd git:(master) ✗ just send_request2
curl -X POST http://localhost:$(just port 8194)/v1/completions -H "Content-Type: application/json" -d '{ "model": "deepseek-ai/DeepSeek-V4-Flash", "prompt": "Can you complete this latin sentence: Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.", "max_tokens": 150, "temperature": 0.0 }'
{"id":"cmpl-babf270348341bbc","object":"text_completion","created":1778253938,"prompt_routed_experts":null,"model":"deepseek-ai/DeepSeek-V4-Flash","choices":[{"index":0,"text":"","logprobs":null,"finish_reason":"stop","stop_reason":null,"token_ids":null,"prompt_logprobs":null,"prompt_token_ids":null,"routed_experts":null}],"service_tier":null,"system_fingerprint":"vllm-0.20.2rc1.dev140+g4140faa4a-dp4-ep-221f27d0","usage":{"prompt_tokens":125,"total_tokens":126,"completion_tokens":1,"prompt_tokens_details":null},"kv_transfer_params":null}%
(llmd) NickLucche@nma-frk-sa-h100-00-preserve ➜  llmd git:(master) ✗ just send_request2
curl -X POST http://localhost:$(just port 8194)/v1/completions -H "Content-Type: application/json" -d '{ "model": "deepseek-ai/DeepSeek-V4-Flash", "prompt": "Can you complete this latin sentence: Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.", "max_tokens": 150, "temperature": 0.0 }'
{"id":"cmpl-9c6f2b1941545af4","object":"text_completion","created":1778253946,"prompt_routed_experts":null,"model":"deepseek-ai/DeepSeek-V4-Flash","choices":[{"index":0,"text":"","logprobs":null,"finish_reason":"stop","stop_reason":null,"token_ids":null,"prompt_logprobs":null,"prompt_token_ids":null,"routed_experts":null}],"service_tier":null,"system_fingerprint":"vllm-0.20.2rc1.dev140+g4140faa4a-dp4-ep-221f27d0","usage":{"prompt_tokens":125,"total_tokens":126,"completion_tokens":1,"prompt_tokens_details":null},"kv_transfer_params":null}%
(llmd) NickLucche@nma-frk-sa-h100-00-preserve ➜  llmd git:(master) ✗ just send_request2
curl -X POST http://localhost:$(just port 8194)/v1/completions -H "Content-Type: application/json" -d '{ "model": "deepseek-ai/DeepSeek-V4-Flash", "prompt": "Can you complete this latin sentence: Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.", "max_tokens": 150, "temperature": 0.0 }'
{"id":"cmpl-a5b2d4e57ea77345","object":"text_completion","created":1778253950,"prompt_routed_experts":null,"model":"deepseek-ai/DeepSeek-V4-Flash","choices":[{"index":0,"text":"","logprobs":null,"finish_reason":"stop","stop_reason":null,"token_ids":null,"prompt_logprobs":null,"prompt_token_ids":null,"routed_experts":null}],"service_tier":null,"system_fingerprint":"vllm-0.20.2rc1.dev140+g4140faa4a-dp4-ep-221f27d0","usage":{"prompt_tokens":125,"total_tokens":126,"completion_tokens":1,"prompt_tokens_details":null},"kv_transfer_params":null}%
(llmd) NickLucche@nma-frk-sa-h100-00-preserve ➜  llmd git:(master) ✗ just send_request2
curl -X POST http://localhost:$(just port 8194)/v1/completions -H "Content-Type: application/json" -d '{ "model": "deepseek-ai/DeepSeek-V4-Flash", "prompt": "Can you complete this latin sentence: Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.", "max_tokens": 150, "temperature": 0.0 }'
{"id":"cmpl-ae1d1d42855c1cca","object":"text_completion","created":1778253952,"prompt_routed_experts":null,"model":"deepseek-ai/DeepSeek-V4-Flash","choices":[{"index":0,"text":"","logprobs":null,"finish_reason":"stop","stop_reason":null,"token_ids":null,"prompt_logprobs":null,"prompt_token_ids":null,"routed_experts":null}],"service_tier":null,"system_fingerprint":"vllm-0.20.2rc1.dev140+g4140faa4a-dp4-ep-221f27d0","usage":{"prompt_tokens":125,"total_tokens":126,"completion_tokens":1,"prompt_tokens_details":null},"kv_transfer_params":null}%
(llmd) NickLucche@nma-frk-sa-h100-00-preserve ➜  llmd git:(master) ✗ just send_request2
curl -X POST http://localhost:$(just port 8194)/v1/completions -H "Content-Type: application/json" -d '{ "model": "deepseek-ai/DeepSeek-V4-Flash", "prompt": "Can you complete this latin sentence: Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.", "max_tokens": 150, "temperature": 0.0 }'
{"id":"cmpl-97180f58b9d4d992","object":"text_completion","created":1778253953,"prompt_routed_experts":null,"model":"deepseek-ai/DeepSeek-V4-Flash","choices":[{"index":0,"text":"","logprobs":null,"finish_reason":"stop","stop_reason":null,"token_ids":null,"prompt_logprobs":null,"prompt_token_ids":null,"routed_experts":null}],"service_tier":null,"system_fingerprint":"vllm-0.20.2rc1.dev140+g4140faa4a-dp4-ep-221f27d0","usage":{"prompt_tokens":125,"total_tokens":126,"completion_tokens":1,"prompt_tokens_details":null},"kv_transfer_params":null}%
(llmd) NickLucche@nma-frk-sa-h100-00-preserve ➜  llmd git:(master) ✗ just send_request2
curl -X POST http://localhost:$(just port 8194)/v1/completions -H "Content-Type: application/json" -d '{ "model": "deepseek-ai/DeepSeek-V4-Flash", "prompt": "Can you complete this latin sentence: Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.", "max_tokens": 150, "temperature": 0.0 }'
{"id":"cmpl-a12ae05e1285ca20","object":"text_completion","created":1778253954,"prompt_routed_experts":null,"model":"deepseek-ai/DeepSeek-V4-Flash","choices":[{"index":0,"text":"","logprobs":null,"finish_reason":"stop","stop_reason":null,"token_ids":null,"prompt_logprobs":null,"prompt_token_ids":null,"routed_experts":null}],"service_tier":null,"system_fingerprint":"vllm-0.20.2rc1.dev140+g4140faa4a-dp4-ep-221f27d0","usage":{"prompt_tokens":125,"total_tokens":126,"completion_tokens":1,"prompt_tokens_details":null},"kv_transfer_params":null}%                                                                                                        (llmd) NickLucche@nma-frk-sa-h100-00-preserve ➜  llmd git:(master) ✗

although sometimes the model response is correct

(llmd) NickLucche@nma-frk-sa-h100-00-preserve ➜  llmd git:(master) ✗ just send_request2
curl -X POST http://localhost:$(just port 8194)/v1/completions -H "Content-Type: application/json" -d '{ "model": "deepseek-ai/DeepSeek-V4-Flash", "prompt": "Can you complete this latin sentence: Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.", "max_tokens": 150, "temperature": 0.0 }'


{"id":"cmpl-ab1152b3bdfbaf04","object":"text_completion","created":1778254046,"prompt_routed_experts":null,"model":"deepseek-ai/DeepSeek-V4-Flash","choices":[{"index":0,"text":" Et harum quidem rerum facilis est et expedita distinctio. Nam libero tempore, cum soluta nobis est eligendi optio cumque nihil impedit quo minus id quod maxime placeat facere possimus, omnis voluptas assumenda est, omnis dolor repellendus. Temporibus autem quibusdam et aut officiis debitis aut rerum necessitatibus saepe eveniet ut et voluptates repudiandae sint et molestiae non recusandae. Itaque earum rerum hic tenetur a sapiente delectus, ut aut reiciendis voluptatibus maiores alias consequatur aut perferendis doloribus asperiores repellat. Lorem ipsum","logprobs":null,"finish_reason":"length","stop_reason":null,"token_ids":null,"prompt_logprobs":null,"prompt_token_ids":null,"routed_experts":null}],"service_tier":null,"system_fingerprint":"vllm-0.20.2rc1.dev140+g4140faa4a-dp4-ep-221f27d0","usage":{"prompt_tokens":125,"total_tokens":275,"completion_tokens":150,"prompt_tokens_details":null},"kv_transfer_params":null}%

despite temperature 0 (no prefix caching). This has no effect on lm-eval scores as far as I could test for this model.

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

vllm - 💡(How to fix) Fix [Bug]: Dsv4-Flash blank `/v1/completions` response