-
Notifications
You must be signed in to change notification settings - Fork 80
Issues
is:issue state:open
is:issue state:open
Issue creation is restricted in this repository
Search results
[Bug]: 5并发,同样的提示词跑3轮,日志里显示Prefix cache hit rate也只有21.3%,正常不应该这么低的。
bugSomething isn't workingSomething isn't workingStatus: Open.#90 In 1CatAI/1Cat-vLLM;- Status: Open.#89 In 1CatAI/1Cat-vLLM;
[Bug]: gptq_marlin_repack has no SM70 kernel image in the official 1.2.1 wheel
bugSomething isn't workingSomething isn't workingStatus: Open.#87 In 1CatAI/1Cat-vLLM;[Bug]: [Upstream Sync] Support system-role messages inside Anthropic Messages API messages array (follow vllm-project/vllm#44283)
bugSomething isn't workingSomething isn't workingStatus: Open.#86 In 1CatAI/1Cat-vLLM;- Status: Open.#85 In 1CatAI/1Cat-vLLM;
- Status: Open.#84 In 1CatAI/1Cat-vLLM;
- Status: Open.#83 In 1CatAI/1Cat-vLLM;
- Status: Open.#82 In 1CatAI/1Cat-vLLM;
[Bug]: v1.2.1执行vllm bench serve 报错
bugSomething isn't workingSomething isn't workingStatus: Open.#81 In 1CatAI/1Cat-vLLM;- Status: Open.#78 In 1CatAI/1Cat-vLLM;
[Bug]: v0.0.2非常省显存,新版本太费显存
bugSomething isn't workingSomething isn't workingStatus: Open.#76 In 1CatAI/1Cat-vLLM;- Status: Open.#75 In 1CatAI/1Cat-vLLM;