Issues du dépôt
lm-sys/FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Issues
Ouverte
TensorRT-LLM backend support?
enhancementgood first issue
3 commentaires7 réactions0 assignés
Ouverte
Please support fastllm
good first issue
2 commentaires0 réactions0 assignés
Ouverte
Support microsoft phi-1.5 model
good first issue
4 commentaires0 réactions0 assignés
Ouverte
[Feature request] Support loading GGUF and GGML model format
good first issue
5 commentaires7 réactions0 assignés
Ouverte
[Feature Request] Support InternLM Deploy
good first issue
2 commentaires0 réactions0 assignés
Ouverte
Need to support Baichuan2
good first issue
11 commentaires12 réactions0 assignés
Ouverte
Issues with VLLM Integration Speedup
good first issue
4 commentaires0 réactions0 assignés
Ouverte
XVERSE-13B need support!
good first issue
1 commentaire0 réactions0 assignés
Ouverte
[Feature] Do you have plan to support multimodal mode?
good first issue
1 commentaire1 réaction0 assignés
Ouverte
[Feature Request] Add a ctranslate2 model worker
enhancementgood first issue
2 commentaires1 réaction1 assigné
Ouverte
Add model C1.2 from Character.ai?
good first issue
3 commentaires0 réactions0 assignés
Ouverte
RWKV-raven and RWKV-world have different prompt template
good first issue
3 commentaires0 réactions0 assignés
Ouverte
4 commentaires1 réaction0 assignés
Ouverte
presence_penalty and repetition_penalty in completions endpoint
good first issue
1 commentaire0 réactions0 assignés
Ouverte
support for 4bit quantization from transfomer library.
enhancementgood first issue
7 commentaires2 réactions0 assignés
Ouverte
tiiuae/falcon-7b does not work on Apple M1 GPU (MPS)
good first issue
2 commentaires1 réaction0 assignés
Ouverte
Support fastchat-t5-3b-v1.0 on M2 GPU model
good first issue
1 commentaire0 réactions0 assignés
Ouverte
Any plans to add AutoGPTQ as a gptq load option?
good first issue
1 commentaire0 réactions0 assignés
Ouverte
Chat Arena version of fastchat-t5-3b-v1.0 provides more refined answers than standard Huggingface model.
documentationgood first issuequestion
26 commentaires3 réactions1 assigné
Ouverte
[BUG] RWKV Models are not configured to use Cuda GPU lists.
buggood first issue
2 commentaires0 réactions0 assignés