1
0
AlpinDale 3bb0f07461 chore: rename `task_handler` to `worker` (#985) 2 сар өмнө
..
__init__.py adb6982090 models: add support for IBM Granite (PowerLM) models (#978) 2 сар өмнө
arctic.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
baichuan.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
bart.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
blip.py f56d6b396a vlm: fallback to SDPA for ViT models on CPU backend (#982) 2 сар өмнө
blip2.py b4a1e2fd02 vlm: add tensor parallel support for vision transformer models (#971) 2 сар өмнө
bloom.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
chameleon.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
chatglm.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
clip.py f56d6b396a vlm: fallback to SDPA for ViT models on CPU backend (#982) 2 сар өмнө
commandr.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
dbrx.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
decilm.py 9022c6d869 remove progress_bar imports 4 сар өмнө
deepseek.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
deepseek_v2.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
eagle.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
exaone.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
falcon.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
fuyu.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
gemma.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
gemma2.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
gpt2.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
gpt_bigcode.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
gpt_j.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
gpt_neox.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
granite.py adb6982090 models: add support for IBM Granite (PowerLM) models (#978) 2 сар өмнө
idefics2_vision_model.py f1d0b77c92 [0.6.0] Release Candidate (#481) 6 сар өмнө
interfaces.py 0b8b407b6d feat: support profiling with multiple multi-modal inputs per prompt (#712) 6 сар өмнө
intern_vit.py f56d6b396a vlm: fallback to SDPA for ViT models on CPU backend (#982) 2 сар өмнө
internlm2.py 7632f91429 fix: InternLM2 model with Tensor Parallel (#980) 2 сар өмнө
internvl.py a8bdd488b9 distributed: support pipeline parallelism for internvl and internlm2 (#965) 2 сар өмнө
jais.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
jamba.py 3bb0f07461 chore: rename `task_handler` to `worker` (#985) 2 сар өмнө
llama.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
llama_embedding.py 9022c6d869 remove progress_bar imports 4 сар өмнө
llava.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
llava_next.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
mamba.py 3bb0f07461 chore: rename `task_handler` to `worker` (#985) 2 сар өмнө
mamba_cache.py bf88c8567e feat: mamba model support (#674) 6 сар өмнө
medusa.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
minicpm.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
minicpmv.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
mixtral.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
mixtral_quant.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
mlp_speculator.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
mpt.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
na_vit.py 9f3e7c86e2 feat: add fused Marlin MoE kernel (#934) 2 сар өмнө
nemotron.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
olmo.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
olmoe.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
opt.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
orion.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
paligemma.py f56d6b396a vlm: fallback to SDPA for ViT models on CPU backend (#982) 2 сар өмнө
persimmon.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
phi.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
phi3_small.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
phi3v.py b4a1e2fd02 vlm: add tensor parallel support for vision transformer models (#971) 2 сар өмнө
phimoe.py 201db10f02 models: add support for Phi3 MoE 2 сар өмнө
qwen.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
qwen2.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
qwen2_moe.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
siglip.py f56d6b396a vlm: fallback to SDPA for ViT models on CPU backend (#982) 2 сар өмнө
solar.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
stablelm.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
starcoder2.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
ultravox.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө
utils.py a8bdd488b9 distributed: support pipeline parallelism for internvl and internlm2 (#965) 2 сар өмнө
xverse.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) 2 сар өмнө