- 21 Jul, 2023 1 commit
-
-
Li Zhang authored
* add GQA for llama2 * fix model conversion * fix lint & remove dev log * update news * minor * fix allocation size * fix split_dim for w_qkv.bias
-
- 05 Jul, 2023 3 commits
-
-
q.yao authored
-
pppppM authored
* add cal qparams * support offload inference * add collect funtions (mod,weight) * stats kv scales * update init * add user guide * fix hints * fix comments & support turbomind format * update user guide * fix slice kv cache error & support pileval dataset (used in llm-awq) * fix wrong num heads slice * update default dataset * fix conflict * fix hints * fix hints * add gitignore
-
q.yao authored
* wip * wip * example finish * fix include and namespace * wtf * install lib * batchize * update cmake install * multithread * fix comment * fix * add mmengine * bind llamamodel --------- Co-authored-by:grimoire <yaoqian@pjlab.org.cn>
-
- 04 Jul, 2023 1 commit
-
-
lvhan028 authored
* check-in script for tokenizing a file * use max_input_len
-
- 03 Jul, 2023 1 commit
-
-
lvhan028 authored
-
- 01 Jul, 2023 3 commits
-
-
lvhan028 authored
* change target tritonfastertransformerbackend to tritonturbomindbackend * install targets to backends/turbomind * changge model_dir
-
lvhan028 authored
* build turbomind * change namespace fastertransformer to turbomind * change logger name
-
AllentDan authored
* temp * fix lint * csrc->src * remove clang-format * skip .rst * skip doc * clang-format version version * mat_B
-
- 29 Jun, 2023 1 commit
-
-
q.yao authored
* add hf tokenizer * format * fix for comment * don't skip speical tokens
-
- 28 Jun, 2023 1 commit
-
-
Li Zhang authored
-
- 22 Jun, 2023 1 commit
-
-
lvhan028 authored
* remove constraints on model name * remove duplicate model converter
-
- 20 Jun, 2023 1 commit
-
-
Li Zhang authored
* add ft code * gitignore * fix lint * revert fmha
-