FasterDecoding/Medusa Issues
Using Medusa with Whisper
Updated 5PPL compute
UpdatedMedusa Training Loss
Updated 5train medusa stage-2
Updated 1mistral.json
UpdatedTraining Medusa heads
Updated 5Cant it support chatgllm?
UpdatedHYDRA support?
UpdatedMisleading Name LLM Name MEDUSA
Updatedabout Medusa mask details
Closedrelease medusa-llm v1.0
Closed 1deepspeed support
UpdatedMedusa 1 and 2 speed up
Closed 2OSError
Updated 3Question about Heads warmup
Updated 1Can I make an AWQ quantization?
Closed 1Results for different configs
Closed 8FasterTransformer support
Updated 1[Feature Request] Qwen model support
Updated 1