| .. |
|
fused_moe
|
201db10f02
models: add support for Phi3 MoE
|
2 mesiacov pred |
|
mamba
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 mesiacov pred |
|
ops
|
8a71788372
Add OLMoE (#772)
|
4 mesiacov pred |
|
__init__.py
|
07aa2a492f
upstream: add option to specify tokenizer
|
1 rok pred |
|
activation.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 mesiacov pred |
|
layernorm.py
|
bfc3da41ae
feat: add torch.compile for GemmaRMSNorm (#898)
|
2 mesiacov pred |
|
linear.py
|
dcb36de9c4
quants: add support for NVIDIA's ModelOpt checkpoints (#1013)
|
2 mesiacov pred |
|
logits_processor.py
|
0e558e9b2f
fix: loading chameleon model with TP>1 (#695)
|
6 mesiacov pred |
|
pooler.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 mesiacov pred |
|
rejection_sampler.py
|
e3a53712f2
fix: mlpspeculator with padded vocab (#669)
|
6 mesiacov pred |
|
resampler.py
|
548e864404
models: add support for QwenVL (#995)
|
2 mesiacov pred |
|
rotary_embedding.py
|
411ac4f405
vlm: add support for Qwen2-VL model (#1015)
|
2 mesiacov pred |
|
sampler.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 mesiacov pred |
|
spec_decode_base_sampler.py
|
09b82f9963
feat: Add support for GPU device selection in SpecDecodeBaseSampler (#629)
|
6 mesiacov pred |
|
typical_acceptance_sampler.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 mesiacov pred |
|
vocab_parallel_embedding.py
|
83af2524f3
quants: add GPTQ and FBGEMM to AphroditeParameters (#987)
|
2 mesiacov pred |
AlpinDale
411ac4f405
vlm: add support for Qwen2-VL model (#1015)