"megatron/core/pipeline_parallel/schedules.py" did not exist on "c1e4526bb35f29ac45077e5243530215d4b6e63c"
- 09 Oct, 2023 1 commit
-
-
Lyu Han authored
* change shared_instances_ from weakptr to sharedptr * update
-
- 26 Sep, 2023 1 commit
-
-
Lyu Han authored
* Fix memory leak * modern c++
-
- 18 Sep, 2023 1 commit
-
-
Chen Xin authored
* reduce gil switching * ffi lock func * remove unused * remove unused * remove unused
-
- 14 Sep, 2023 1 commit
-
-
Chen Xin authored
-
- 11 Sep, 2023 1 commit
-
-
Lyu Han authored
* tmp * add demo for codellama inference * update * update * update * update codellama.md * export rope_theta * update * update doc * fix client.py * define SamplingParam * rollback 'end' * rotary_emb_base to rotary_embedding_base * change to baichuan2-7b
-
- 18 Aug, 2023 1 commit
-
-
Li Zhang authored
* qwen support * dynamic ntk & logn attn * fix ntk & add chat template * fix ntk scaling & stop words * fix lint * add tiktoken to requirements.txt * fix tokenizer, set model format automatically * update model.py * update readme * fix lint
-
- 17 Aug, 2023 1 commit
-
-
Chen Xin authored
* __PRETTY_FUNCTION__ * CASE_K * uint * remove not * HALF_FLT_MAX * struct init * port utils * better build pthread-win32 * port kernels * port utils/gemm_test * hide windows header * port models * port examples && triton_backend && unittests * update build readme * fix lint * fix lint * fix lint * fix lint * fix lint * fix build * fix build * cmake version * fix typos * update ci * port kernels/gemm_s_f16 * update ci * fix ci * use cudaStreamSynchronize instead of volatile check * remove gettimeofday * remove pthread-win32 * remove dirent.h * update pre-commit * update * remove todo * fix include * fix build * fix build * fix build ci * fix github action trigger * update README * fix linux-build ci * remove windows folder * fix lint * update readme
-
- 14 Aug, 2023 1 commit
-
-
Li Zhang authored
* add w4a16 * fix `deploy.py` * add doc * add w4a16 kernels * fuse w1/w3 & bugfixes * fix typo * python * guard sm75/80 features * add missing header * refactor * qkvo bias * update cost model * fix lint * update `deploy.py`
-
- 24 Jul, 2023 1 commit
-
-
Li Zhang authored
* decode only forward pass * fix lint * batch embedding
-
- 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
-
- 01 Jul, 2023 2 commits