Halaman utama Jelajahi Bantuan
Daftar Masuk
david
/
aphrodite-engine
cermin dari https://github.com/PygmalionAI/aphrodite-engine
1
0
Fork 0
Berkas Masalah 0 Wiki
Pohon: ed6717d0c0
Ranting Tag
aphrodite-engin...
/
aphrodite
/
modeling
/
models
AlpinDale acbdc50a71 fix: `vocab_size` field access in llava 5 bulan lalu
..
__init__.py fa15bad2ea chore: minor AMD fixes 5 bulan lalu
arctic.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
baichuan.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
bloom.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
chameleon.py a0d031efcc feat: initial text-to-text support for Chameleon model 5 bulan lalu
chatglm.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
clip.py e26a4ac698 chore: avoid loading the unused layers and init the VLM up to the required feature space 5 bulan lalu
commandr.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
dbrx.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
decilm.py 56e0b8223c chore: add base class for LoRA-supported models 6 bulan lalu
deepseek.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
deepseek_v2.py 1efd0f89b7 feat: support FP8 for DeepSeekV2 MoE 5 bulan lalu
falcon.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
fuyu.py e13a66925c feat: add fuyu vision model and persimmon language model support 5 bulan lalu
gemma.py 05e45aeb53 fix: dtype mismatch for paligemma 5 bulan lalu
gemma2.py 5761ef8c35 feat: gemma-2 support 5 bulan lalu
gpt2.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
gpt_bigcode.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
gpt_j.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
gpt_neox.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
interfaces.py e76bbe72eb chore: handle aborted requests for jamba 5 bulan lalu
internlm2.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
jais.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
jamba.py f5d52320da Port mamba kernels to Aphrodite (#595) 5 bulan lalu
llama.py 00503b9fc1 feat: non-uniform quantization via `compressed-tensors` for llama 5 bulan lalu
llama_embedding.py 50b7c13db0 refactor: attention selector (#552) 6 bulan lalu
llava.py acbdc50a71 fix: `vocab_size` field access in llava 5 bulan lalu
llava_next.py acbdc50a71 fix: `vocab_size` field access in llava 5 bulan lalu
medusa.py d9f4c36edd feat: Medusa speculative decoding support (#590) 5 bulan lalu
minicpm.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
mixtral.py 00503b9fc1 feat: non-uniform quantization via `compressed-tensors` for llama 5 bulan lalu
mixtral_quant.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
mlp_speculator.py db73f03cdc fix: use ParallelLMHead for MLPSpeculator 5 bulan lalu
mpt.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
olmo.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
opt.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
orion.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
paligemma.py 05e45aeb53 fix: dtype mismatch for paligemma 5 bulan lalu
persimmon.py e13a66925c feat: add fuyu vision model and persimmon language model support 5 bulan lalu
phi.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
phi3_small.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
phi3v.py ad68d149d8 chore: refactor and decouple phi3v image embedding 5 bulan lalu
qwen.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
qwen2.py fb4c01740c feat: add asymmetric TP support for Qwen2 5 bulan lalu
qwen2_moe.py 1efd0f89b7 feat: support FP8 for DeepSeekV2 MoE 5 bulan lalu
stablelm.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
starcoder2.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu
utils.py 00503b9fc1 feat: non-uniform quantization via `compressed-tensors` for llama 5 bulan lalu
xverse.py 0f4a9ee77b quantized lm_head (#582) 5 bulan lalu