Bug Int4 Issue 349 Internlmlmdeploy Github
a bug · Issue #81 · InternLM/lmdeploy · GitHub
LLama Int4 AWQ (W4A8) Fails · Issue #1084 · NVIDIA/TensorRT-LLM · GitHub
[Bug] INT4模型输出乱码 · Issue #349 · InternLM/lmdeploy · GitHub
int4量化版本运行报错 · Issue #45 · OpenMOSS/MOSS · GitHub
![[BUG/Help] · Issue #562 · zai-org/ChatGLM-6B · GitHub](https://user-images.githubusercontent.com/78424351/231521150-45967d79-75bf-4f99-86ae-f9e1449ead28.png)
[BUG/Help] · Issue #562 · zai-org/ChatGLM-6B · GitHub
[Bug] · Issue #349 · lencx/ChatGPT · GitHub
use internVL debug · Issue #240 · om-ai-lab/VLM-R1 · GitHub
[Bug] 模型部署中遇到奇怪的问题 · Issue #2436 · open-mmlab/mmdeploy · GitHub
[BUG] · Issue #460 · QwenLM/Qwen · GitHub
[BUG] 无法加载internlm-20b · Issue #142 · ModelTC/lightllm · GitHub
Advertisement Space (300x250)
[QST]Bugs when using int4 gemm in python · Issue #756 · NVIDIA/cutlass ...
[BUG] Install error · Issue #349 · MustardChef/WSABuilds · GitHub
[Feature Request]: Support INT4 for MiniCPM-Llama3-V-2_5 · Issue #6932 ...
[BUG]: LLMs not loading · Issue #1644 · Mintplex-Labs/anything-llm · GitHub
![[Bug]: chatGLM_int4 加载失败 · Issue #585 · GaiZhenbiao/ChuanhuChatGPT · GitHub](https://user-images.githubusercontent.com/49812095/230929800-db708a41-8a46-4d6e-acee-1bc44255a51b.png)
[Bug]: chatGLM_int4 加载失败 · Issue #585 · GaiZhenbiao/ChuanhuChatGPT · GitHub
请问2.5支持int4的量化推理吗？ · Issue #353 · InternLM/InternLM-XComposer · GitHub
[Bug]: · Issue #26549 · vllm-project/vllm · GitHub
Issue · GitHub
Effect of the bug in ingroup_inds op · Issue #1418 · open-mmlab ...
Issue · GitHub
Advertisement Space (336x280)
[Bug] 分布式训练代码例子报错， · Issue #1540 · open-mmlab/mmengine · GitHub
INT4模型 · Issue #83 · ssbuild/chatglm_finetuning · GitHub
代码bugs · Issue #25 · intro-llm/intro-llm.github.io · GitHub
[Bug] 关于流式并发相关 · Issue #1557 · InternLM/lmdeploy · GitHub
LLM Plugin Injection · Issue #6 · mitre/secure-coding-case-studies · GitHub
Releasing model? · Issue #1 · InternLM/InternLM-techreport · GitHub
复读严重 · Issue #28 · InternLM/InternLM · GitHub
![[Bug] · Issue #1441 · open-mmlab/mmdeploy · GitHub](https://user-images.githubusercontent.com/55951697/203981583-546e55f3-3920-4313-86de-4095075785e0.png)
[Bug] · Issue #1441 · open-mmlab/mmdeploy · GitHub
请求int4量化模型 · Issue #18 · QwenLM/Qwen · GitHub
[Feature] 可以在不联网的时候，直接使用本地模型 · Issue #4071 · InternLM/lmdeploy · GitHub
Advertisement Space (336x280)
int8没问题，int4部署报错 · Issue #116 · baichuan-inc/Baichuan-13B · GitHub
int · Issue #23 · om-ai-lab/VLM-R1 · GitHub
Batch推理方式 · Issue #219 · InternLM/lmdeploy · GitHub
训练报错 · Issue #1929 · open-mmlab/mmdeploy · GitHub
+34% higher throughput? · Issue #421 · vllm-project/vllm · GitHub
Baichuan2-7b quantize int4 2tp ,tritonserver launch failed · Issue #391 ...