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