-
Notifications
You must be signed in to change notification settings - Fork 256
Issues
is:issue state:open
is:issue state:open
Issue creation is restricted in this repository
Search results
[Question]: models/llm/qwen3_5.h 必须编译 NPU 头文件,而不是 common 的
questionFurther information is requestedFurther information is requestedStatus: Open.#1916 In xLLM-AI/xllm;[Question]: deepseek-v4-flash模型,哪个版本支持,哪个commit号?
questionFurther information is requestedFurther information is requestedStatus: Open.#1913 In xLLM-AI/xllm;[Question]: 请问BW1000 上部署Minimax M3/M2.7,token吞吐率实测效果咋样?是否支持专家并行?
questionFurther information is requestedFurther information is requestedStatus: Open.#1905 In xLLM-AI/xllm;[Question]: A3单机跑GLM5.2-W8A8最大支持多少上下文?
questionFurther information is requestedFurther information is requestedStatus: Open.#1862 In xLLM-AI/xllm;- Status: Open.#1851 In xLLM-AI/xllm;
- Status: Open.#1837 In xLLM-AI/xllm;
[Question]: Missing MTTOplib
questionFurther information is requestedFurther information is requestedStatus: Open.#1557 In xLLM-AI/xllm;[Bug]: CUDA enable_graph=true下运行ais_bench GSM8K 测试失败
bugSomething isn't workingSomething isn't workingStatus: Open.#1550 In xLLM-AI/xllm;[Bug]: ACL Graph 模式下 ATB CustomPagedAttention context_lens 冻结导致 decode 全零输出
bugSomething isn't workingSomething isn't workingStatus: Open.#1466 In xLLM-AI/xllm;- Status: Open.#1016 In xLLM-AI/xllm;
[Question]: GLM-5-W8A8如何配置tool-call-parser和reasoning_parser
questionFurther information is requestedFurther information is requestedStatus: Open.#1004 In xLLM-AI/xllm;[Question]: 想问下将来有可能适配Atlas 300I 系列的NPU吗
questionFurther information is requestedFurther information is requestedStatus: Open.#995 In xLLM-AI/xllm;