Support For Constrained Decoding Issue 288 Vllm Projectvllm Github
Support for Constrained decoding · Issue #288 · vllm-project/vllm · GitHub
Diving into speculative decoding training support for vLLM with ...
[Model]: Support for InternVL2 · Issue #6321 · vllm-project/vllm · GitHub
[Feature]: Add Support for Guided Decoding (Structured Output) · Issue ...
can vllm support loading lora? · Issue #2710 · vllm-project/vllm · GitHub
Can vLLM support medusa head? · Issue #1023 · vllm-project/vllm · GitHub
Will vLLM supports Self-Speculative Decoding ？ · Issue #2559 · vllm ...
Support VLM model and GPT4V API · Issue #2058 · vllm-project/vllm · GitHub
[Usage]: Does vLLM support multi-task · Issue #13390 · vllm-project ...
Does vllm support CPU? · vllm-project vllm · Discussion #999 · GitHub
Advertisement Space (300x250)
[Installation]: vLLM does not support torch 2.5 · Issue #9554 · vllm ...
vLLM Development Roadmap · Issue #244 · vllm-project/vllm · GitHub
[Feature]: is vllm support sequence-parallel？ · Issue #3940 · vllm ...
InternLM 20B Support · Issue #1411 · vllm-project/vllm · GitHub
Quantization support · vllm-project vllm · Discussion #856 · GitHub
[Bug]: VLLM doesn't support LoRa with config `modules_to_save` · Issue ...
Greedy decoding generates different outputs · Issue #1202 · vllm ...
Can vLLM support the Yi-34B model? · Issue #1554 · vllm-project/vllm ...
[Bug]: vllm 0.5.4 NCCL error when applying speculative decoding · Issue ...
[RFC]: Deprecating vLLM V0 · Issue #18571 · vllm-project/vllm · GitHub
Advertisement Space (336x280)
vllm not support W8A8_Int8 deepseek_v2 · Issue #859 · vllm-project/llm ...
usage of vllm for extracting embeddings · Issue #1654 · vllm-project ...
[Misc]: fp8 support · Issue #6246 · vllm-project/vllm · GitHub
[Usage]: Prefix caching in VLLM · Issue #5176 · vllm-project/vllm · GitHub
[New Model]: CohereForCausalLM Support request · Issue #3546 · vllm ...
[Usage]: Using VLLM with Langchain for RAG purposes · Issue #5572 ...
[Bug]: Speculative decoding cannot match tokens · Issue #6285 · vllm ...
Speculative Decoding in vLLM | OpenLM.ai
vLLM 学习笔记｜Guided Decoding · Home
[Installation]: Failed to build vLLM from source · Issue #18380 · vllm ...
Advertisement Space (336x280)
Structured Decoding in vLLM: a gentle introduction | vLLM Blog
How Speculative Decoding Boosts vLLM Performance by up to 2.8x | vLLM Blog
vLLM Distributed Inference stuck when using multi -GPU · Issue #2466 ...
Does vllm change the output of LLM? · Issue #2657 · vllm-project/vllm ...
how can vllm support function_call · vllm-project vllm · Discussion ...
RuntimeError: vLLM cannot currently support max_model_len=65536 with ...