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