Commits · 981a46104682e1aaaa76efca3491b2a5ef81b918 · OpenDAS / Lmdeploy

"src/diffusers/models/unets/unet_i2vgen_xl.py" did not exist on "84b82a6cb7045de687684c23caa7683d43a7cd9d"

31 Jul, 2023 1 commit
- [Fix] Remove unused code to reduce binary size (#181) · 981a4610
  Li Zhang authored Jul 31, 2023
```
* clean-up

* fix lint

* fix lint
```
  981a4610
21 Jul, 2023 1 commit

[Feature] Support Llama-2 with GQA (#147) · f07b697b

Li Zhang authored Jul 21, 2023

* 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

f07b697b

01 Jul, 2023 3 commits
- build turbomind (#35) · 35d64462
  lvhan028 authored Jul 01, 2023
```
* build turbomind

* change namespace fastertransformer to turbomind

* change logger name
```
  35d64462
- rename src/fastertransformer to src/turbomind (#33) · 53d2e42c
  lvhan028 authored Jul 01, 2023
  
  53d2e42c
- Add lint action (#32) · fe46dac2
  AllentDan authored Jul 01, 2023
```
* temp

* fix lint

* csrc->src

* remove clang-format

* skip .rst

* skip doc

* clang-format

version

version

* mat_B
```
  fe46dac2
28 Jun, 2023 1 commit

feat(src): add kv cache int8 quantization (#22) · cc93136e

tpoisonooo authored Jun 28, 2023

* feat(src): add int8 and compile passed

* feat(kernels): fix

* feat(llama): update kernel

* feat(src): add debug

* fix(kernel): k_cache use int8_t pointer

* style(llama): clean code

* feat(deploy.py): revert to enable fmha

* style(LlamaV2): clean code

* feat(deploy.py): add default quant policy

cc93136e

20 Jun, 2023 1 commit
- check-in fastertransformer (#7) · 9efcac38
  Li Zhang authored Jun 20, 2023
```
* add ft code

* gitignore

* fix lint

* revert fmha
```
  9efcac38