thetom-ai/Qwen3.6-27B-ConfigI-MLX
Text Generation • 27B • Updated • 163 • 5
heykb
heykb
·
AI & ML interests
None yet
Recent Activity
new activity about 2 months ago
thetom-ai/Qwen3.6-27B-ConfigI-MLX:May I ask whether MTP (Multi-Token Prediction) is currently supported in vLLM-swift? new activity about 2 months ago
thetom-ai/Qwen3.6-27B-ConfigI-MLX:Fatal error: [metal::Device] Unable to load kernel turbo_dequant_rotated_4_256_bf16. on liked a model about 2 months ago
thetom-ai/Qwen3.6-27B-ConfigI-MLXOrganizations
None yet
May I ask whether MTP (Multi-Token Prediction) is currently supported in vLLM-swift?
2
#1 opened about 2 months ago
by heykb
Fatal error: [metal::Device] Unable to load kernel turbo_dequant_rotated_4_256_bf16. on
2
#2 opened about 2 months ago
by heykb
liked a
model about 2 months ago
mlx_lm.convert tokenizer regex mismatch
1
#2 opened 2 months ago
by heykb
liked a
model 2 months ago
