Search results

GPT-OSS and OpenAI API Enhancements

Status: Open.

#288 In EricLBuehler/candle-vllm;

· sempervictus opened on Aug 28, 2025

Llama-Nemotron Support

Status: Open.

#282 In EricLBuehler/candle-vllm;

· sempervictus opened on Aug 26, 2025

Dynamic Rope Scaling for Llama fails

Status: Open.

#277 In EricLBuehler/candle-vllm;

· sempervictus opened on Aug 25, 2025

Model Request: recurrentgemma

Status: Open.

#276 In EricLBuehler/candle-vllm;

· sempervictus opened on Aug 24, 2025

Feature Request: Quantization Support for DeepSeek

Status: Open.

#274 In EricLBuehler/candle-vllm;

· sempervictus opened on Aug 23, 2025

llama4 text generation support

Status: Open.

#272 In EricLBuehler/candle-vllm;

· sempervictus opened on Aug 21, 2025

DeepSeek v3.1 Support

Status: Open.

#270 In EricLBuehler/candle-vllm;

· sempervictus opened on Aug 19, 2025

Feature Request: HRM Support

Status: Open.

#267 In EricLBuehler/candle-vllm;

· sempervictus opened on Aug 18, 2025

Qwen3 MoE Tool Usage Failures

Status: Open.

#262 In EricLBuehler/candle-vllm;

· sempervictus opened on Aug 14, 2025

Feature Request/Discussion: Host Memory Offload

Status: Open.

#253 In EricLBuehler/candle-vllm;

· sempervictus opened on Aug 8, 2025

<code>Dockerfile</code> should split off separate CUDA + MKL variants

Status: Open.

#243 In EricLBuehler/candle-vllm;

· polarathene opened on Aug 5, 2025

Feature Request: Flash Attention for Older Architectures

Status: Open.

#234 In EricLBuehler/candle-vllm;

· sempervictus opened on Aug 4, 2025