lm-sys/FastChat Issues | Good First Issue

Python (38,959 stars) (4,736 forks) (30 indexed issues) (PR metrics pending)Last commit Jun 2, 2025

Issues

30 open indexed issues

RSS Atom

Open

TensorRT-LLM backend support?

enhancementgood first issue

lm-sys/FastChat #2,595 opened Oct 21, 2023 · Python · 38,959 stars

3 comments7 reactions0 assignees

Open

Please support fastllm

good first issue

lm-sys/FastChat #2,521 opened Oct 6, 2023 · Python · 38,959 stars

2 comments0 reactions0 assignees

Open

Support microsoft phi-1.5 model

good first issue

lm-sys/FastChat #2,435 opened Sep 18, 2023 · Python · 38,959 stars

4 comments0 reactions0 assignees

Open

[Feature request] Support loading GGUF and GGML model format

good first issue

lm-sys/FastChat #2,410 opened Sep 13, 2023 · Python · 38,959 stars

5 comments7 reactions0 assignees

Open

[Feature Request] Support InternLM Deploy

good first issue

lm-sys/FastChat #2,403 opened Sep 12, 2023 · Python · 38,959 stars

2 comments0 reactions0 assignees

Open

Need to support Baichuan2

good first issue

lm-sys/FastChat #2,377 opened Sep 6, 2023 · Python · 38,959 stars

11 comments12 reactions0 assignees

Open

Issues with VLLM Integration Speedup

good first issue

lm-sys/FastChat #2,362 opened Sep 5, 2023 · Python · 38,959 stars

4 comments0 reactions0 assignees

Open

XVERSE-13B need support!

good first issue

lm-sys/FastChat #2,300 opened Aug 24, 2023 · Python · 38,959 stars

1 comment0 reactions0 assignees

Open

[Feature] Do you have plan to support multimodal mode?

good first issue

lm-sys/FastChat #2,216 opened Aug 14, 2023 · Python · 38,959 stars

1 comment1 reaction0 assignees

Open

[Feature Request] Add a ctranslate2 model worker

enhancementgood first issue

lm-sys/FastChat #2,133 opened Aug 1, 2023 · Python · 38,959 stars

2 comments1 reaction1 assignee

Open

Add model C1.2 from Character.ai?

good first issue

lm-sys/FastChat #2,035 opened Jul 20, 2023 · Python · 38,959 stars

3 comments0 reactions0 assignees

Open

RWKV-raven and RWKV-world have different prompt template

good first issue

lm-sys/FastChat #1,929 opened Jul 13, 2023 · Python · 38,959 stars

3 comments0 reactions0 assignees

Open

Support for htttps protocol call between controller node and worker node

good first issue

lm-sys/FastChat #1,915 opened Jul 10, 2023 · Python · 38,959 stars

4 comments1 reaction0 assignees

Open

presence_penalty and repetition_penalty in completions endpoint

good first issue

lm-sys/FastChat #1,914 opened Jul 10, 2023 · Python · 38,959 stars

1 comment0 reactions0 assignees

Open

support for 4bit quantization from transfomer library.

enhancementgood first issue

lm-sys/FastChat #1,798 opened Jun 27, 2023 · Python · 38,959 stars

7 comments2 reactions0 assignees

Open

tiiuae/falcon-7b does not work on Apple M1 GPU (MPS)

good first issue

lm-sys/FastChat #1,746 opened Jun 20, 2023 · Python · 38,959 stars

2 comments1 reaction0 assignees

Open

Support fastchat-t5-3b-v1.0 on M2 GPU model

good first issue

lm-sys/FastChat #1,744 opened Jun 20, 2023 · Python · 38,959 stars

1 comment0 reactions0 assignees

Open

Any plans to add AutoGPTQ as a gptq load option?

good first issue

lm-sys/FastChat #1,671 opened Jun 12, 2023 · Python · 38,959 stars

1 comment0 reactions0 assignees

Open

Chat Arena version of fastchat-t5-3b-v1.0 provides more refined answers than standard Huggingface model.

documentationgood first issuequestion

lm-sys/FastChat #1,264 opened May 15, 2023 · Python · 38,959 stars

26 comments3 reactions1 assignee

Open

[BUG] RWKV Models are not configured to use Cuda GPU lists.

buggood first issue

lm-sys/FastChat #1,248 opened May 15, 2023 · Python · 38,959 stars

2 comments0 reactions0 assignees