ColossalAI

Commit Graph

Author	SHA1	Message	Date
flybird11111	64f74a157e	[NPU]support npu (#6089 ) * support npu * support pretrain support pretrain fix * support lora fix fix * support chatglm fix fxi fix [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci fix fix [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci fix [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci fix fix fix * Update train.py * Update train.py	2024-11-20 15:28:35 +08:00
Edenzzzz	f5c84af0b0	[Feature] Zigzag Ring attention (#5905 ) * halfway * fix cross-PP-stage position id length diff bug * fix typo * fix typo * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * unified cross entropy func for all shardformer models * remove redundant lines * add basic ring attn; debug cross entropy * fwd bwd logic complete * fwd bwd logic complete; add experimental triton rescale * precision tests passed * precision tests passed * fix typos and remove misc files * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * add sp_mode to benchmark; fix varlen interface * update softmax_lse shape by new interface * change tester name * remove buffer clone; support packed seq layout * add varlen tests * fix typo * all tests passed * add dkv_group; fix mask * remove debug statements --------- Co-authored-by: Edenzzzz <wtan45@wisc.edu> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>	2024-08-16 13:56:38 +08:00
Steve Luo	7806842f2d	add paged-attetionv2: support seq length split across thread block (#5707 )	2024-05-14 12:46:54 +08:00
傅剑寒	50104ab340	[Inference/Feat] Add convert_fp8 op for fp8 test in the future (#5706 ) * add convert_fp8 op for fp8 test in the future * rerun ci	2024-05-10 18:39:54 +08:00
Steve Luo	5cd75ce4c7	[Inference/Kernel] refactor kvcache manager and rotary_embedding and kvcache_memcpy oper… (#5663 ) * refactor kvcache manager and rotary_embedding and kvcache_memcpy operator * refactor decode_kv_cache_memcpy * enable alibi in pagedattention	2024-04-30 15:52:23 +08:00
Steve Luo	a8fd3b0342	[Inference/Kernel] Optimize paged attention: Refactor key cache layout (#5643 ) * optimize flashdecodingattention: refactor code with different key cache layout(from [num_blocks, num_kv_heads, block_size, head_size] to [num_blocks, num_kv_heads, head_size/x, block_size, x]) * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>	2024-04-25 14:24:02 +08:00
傅剑寒	279300dc5f	[Inference/Refactor] Refactor compilation mechanism and unified multi hw (#5613 ) * refactor compilation mechanism and unified multi hw * fix file path bug * add init.py to make pybind a module to avoid relative path error caused by softlink * delete duplicated micros * fix micros bug in gcc	2024-04-24 14:17:54 +08:00

7 Commits (support-npu)