EricLBuehler/candle-vllm Issues
Add model support for gemma 9b
Updated 16Support chat serving for more models
Updated 7Support stream response
Closed 7Using candle-vllm as crate in rust?
Updated 1model download failing from HF
Closed 1Qwen 2 model broken
Closed 3LongRope support for Phi 3
Closed 2Doesn't compile
Closed 2[Request] Constrained Generation
Closed 4Support Mixtral-8x7B-v0.1
Closed 2candle-vllm build issue
Closed 1Wrong URL for downloading models
Closed 5`copy_blocks` function
Closed`reshape_and_cache` function
Closed 1Pass tensor pointers
Closed 1`swap_blocks` function
ClosedPagedAttention tracking issue
Closed 4Pipeline batching tracking issue
Closed 3mistral error
Closed 4OpenAI API version
Closed 4KV Cache causes breakage
Closed 2Support streaming of tokens
Closed 1Readme request
Closed 4