sglang

baichuan.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

chatglm.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

commandr.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

dbrx.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

deepseek_v2.py

Support DP MLA (#1970 )

2024-11-16 09:01:43 +00:00

deepseek.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

exaone.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

gemma2_reward.py

[Minor] Remove unused imports (#2006 )

2024-11-11 15:36:14 -08:00

gemma2.py

Rename layer_idx to layer_id for consistency (#2078 )

2024-11-18 13:00:02 -08:00

gemma.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

gpt2.py

fix black in pre-commit (#1940 )

2024-11-08 07:42:47 +08:00

gpt_bigcode.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

grok.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

internlm2_reward.py

support internlm2-reward (#1994 )

2024-11-11 15:09:58 -08:00

internlm2.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

llama_classification.py

[1/N] Remove CacheConfig import in all model files (#1658 )

2024-10-14 09:06:34 -07:00

llama_embedding.py

Let reward model take text inputs instead of message lists (#1907 )

2024-11-03 13:27:12 -08:00

llama_reward.py

[Minor] Remove unused imports (#2006 )

2024-11-11 15:36:14 -08:00

llama.py

Fix weight loading for tied word embedding when TP > 1 (#2009 )

2024-11-11 17:52:42 -08:00

llava.py

Simplify flashinfer indices update for prefill (#2074 )

2024-11-18 00:02:36 -08:00

llavavid.py

Simplify flashinfer indices update for prefill (#2074 )

2024-11-18 00:02:36 -08:00

minicpm3.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

minicpm.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

mistral.py

[Fix] Reduce memory usage for loading llava model & Remove EntryClassRemapping (#1308 )

2024-09-02 21:44:45 -07:00

mixtral_quant.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

mixtral.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

mllama.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

olmo.py

Rename layer_idx to layer_id for consistency (#2078 )

2024-11-18 13:00:02 -08:00

olmoe.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

phi3_small.py

Crash the CI jobs on model import errors (#2072 )

2024-11-17 22:18:11 -08:00

qwen2_moe.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

qwen2_vl.py

Simplify flashinfer indices update for prefill (#2074 )

2024-11-18 00:02:36 -08:00

qwen2.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

qwen.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

stablelm.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

torch_native_llama.py

Turn off autotune for scaled mm for fp8 dynamic quant in torchao (#2116 )

2024-11-21 12:19:49 -08:00

xverse_moe.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

xverse.py

Update vocab embedding deps and add TP switch (#1856 )

2024-10-31 20:13:07 -07:00

yivl.py

[1/N] Remove CacheConfig import in all model files (#1658 )

2024-10-14 09:06:34 -07:00