AlpinDale adb6982090 models: add support for IBM Granite (PowerLM) models (#978) 2 周之前
..
__init__.py adb6982090 models: add support for IBM Granite (PowerLM) models (#978) 2 周之前
arctic.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
baichuan.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
bart.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
blip.py b4a1e2fd02 vlm: add tensor parallel support for vision transformer models (#971) 2 周之前
blip2.py b4a1e2fd02 vlm: add tensor parallel support for vision transformer models (#971) 2 周之前
bloom.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
chameleon.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
chatglm.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
clip.py b4a1e2fd02 vlm: add tensor parallel support for vision transformer models (#971) 2 周之前
commandr.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
dbrx.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
decilm.py 9022c6d869 remove progress_bar imports 2 月之前
deepseek.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
deepseek_v2.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
eagle.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
exaone.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
falcon.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
fuyu.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
gemma.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
gemma2.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
gpt2.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
gpt_bigcode.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
gpt_j.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
gpt_neox.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
granite.py adb6982090 models: add support for IBM Granite (PowerLM) models (#978) 2 周之前
idefics2_vision_model.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 月之前
interfaces.py 0b8b407b6d feat: support profiling with multiple multi-modal inputs per prompt (#712) 4 月之前
intern_vit.py b4a1e2fd02 vlm: add tensor parallel support for vision transformer models (#971) 2 周之前
internlm2.py a8bdd488b9 distributed: support pipeline parallelism for internvl and internlm2 (#965) 2 周之前
internvl.py a8bdd488b9 distributed: support pipeline parallelism for internvl and internlm2 (#965) 2 周之前
jais.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
jamba.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
llama.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
llama_embedding.py 9022c6d869 remove progress_bar imports 2 月之前
llava.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
llava_next.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
mamba.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
mamba_cache.py bf88c8567e feat: mamba model support (#674) 4 月之前
medusa.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
minicpm.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
minicpmv.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
mixtral.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
mixtral_quant.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
mlp_speculator.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
mpt.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
na_vit.py 9f3e7c86e2 feat: add fused Marlin MoE kernel (#934) 2 周之前
nemotron.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
olmo.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
olmoe.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
opt.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
orion.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
paligemma.py b4a1e2fd02 vlm: add tensor parallel support for vision transformer models (#971) 2 周之前
persimmon.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
phi.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
phi3_small.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
phi3v.py b4a1e2fd02 vlm: add tensor parallel support for vision transformer models (#971) 2 周之前
phimoe.py 201db10f02 models: add support for Phi3 MoE 2 周之前
qwen.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
qwen2.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
qwen2_moe.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
siglip.py b4a1e2fd02 vlm: add tensor parallel support for vision transformer models (#971) 2 周之前
solar.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
stablelm.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
starcoder2.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
ultravox.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前
utils.py a8bdd488b9 distributed: support pipeline parallelism for internvl and internlm2 (#965) 2 周之前
xverse.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 周之前