3271 Commits (bdf9a001d61cfad4bb68752c4a808295165307a0)

 

All Branches   

Search

Author	SHA1	Message	Date
Jianghai	730103819d	[Inference]Fused kv copy into rotary calculation (#5383) ... * revise rotary embedding * remove useless print * adapt * fix * add * fix * modeling * fix * fix * fix * fused kv copy * fused copy * colossalai/kernel/triton/no_pad_rotary_embedding.py * del padding llama * del	9 months ago
Stephan Kölker	5d380a1a21	[hotfix] Fix wrong import in meta_registry (#5392)	9 months ago
CZYCW	b833153fd5	[hotfix] fix variable type for top_p (#5313) ... Co-authored-by: binmakeswell <binmakeswell@gmail.com>	9 months ago
Yuanheng Zhao	b21aac5bae	[Inference] Optimize and Refactor Inference Batching/Scheduling (#5367) ... * add kvcache manager funcs for batching * add batch bucket for batching * revise RunningList struct in handler * add kvcache/batch funcs for compatibility * use new batching methods * fix indexing bugs * revise abort logic * use cpu seq lengths/block tables * rm unused attr in Sequence * fix type conversion/default arg * add and revise pytests * revise pytests, rm unused tests * rm unused statements * fix pop finished indexing issue * fix: use index in batch when retrieving inputs/update seqs * use dict instead of odict in batch struct * arg type hinting * fix make compress * refine comments * fix: pop_n_seqs to pop the first n seqs * add check in request handler * remove redundant conversion * fix test for request handler * fix pop method in batch bucket * fix prefill adding	9 months ago
Frank Lee	705a62a565	[doc] updated installation command (#5389)	9 months ago
yixiaoer	69e3ad01ed	[doc] Fix typo (#5361)	9 months ago
Hongxin Liu	7303801854	[llama] fix training and inference scripts (#5384) ... * [llama] refactor inference example to fit sft * [llama] fix training script to fit gemini * [llama] fix inference script	9 months ago
Hongxin Liu	adae123df3	[release] update version (#5380)	10 months ago
Frank Lee	efef43b53c	Merge pull request #5372 from hpcaitech/exp/mixtral	10 months ago
yuehuayingxueluo	8c69debdc7	[Inference]Support vllm testing in benchmark scripts (#5379) ... * add vllm benchmark scripts * fix code style * update run_benchmark.sh * fix code style	10 months ago
Frank Lee	4c03347fc7	Merge pull request #5377 from hpcaitech/example/llama-npu ... [llama] support npu for Colossal-LLaMA-2	10 months ago
Frank Lee	9afa52061f	[inference] refactored config (#5376)	10 months ago
ver217	06db94fbc9	[moe] fix tests	10 months ago
Hongxin Liu	65e5d6baa5	[moe] fix mixtral optim checkpoint (#5344)	10 months ago
Hongxin Liu	956b561b54	[moe] fix mixtral forward default value (#5329)	10 months ago
Hongxin Liu	b60be18dcc	[moe] fix mixtral checkpoint io (#5314)	10 months ago
Hongxin Liu	da39d21b71	[moe] support mixtral (#5309) ... * [moe] add mixtral block for single expert * [moe] mixtral block fwd support uneven ep * [moe] mixtral block bwd support uneven ep * [moe] add mixtral moe layer * [moe] simplify replace * [meo] support save sharded mixtral * [meo] support load sharded mixtral * [meo] support save sharded optim * [meo] integrate moe manager into plug * [meo] fix optimizer load * [meo] fix mixtral layer	10 months ago
Hongxin Liu	c904d2ae99	[moe] update capacity computing (#5253) ... * [moe] top2 allow uneven input * [moe] update capacity computing * [moe] remove debug info * [moe] update capacity computing * [moe] update capacity computing	10 months ago
Xuanlei Zhao	7d8e0338a4	[moe] init mixtral impl	10 months ago
Jianghai	1f8c7e7046	[Inference] User Experience: update the logic of default tokenizer and generation config. (#5337) ... * add * fix * fix * pause * fix * fix pytest * align * fix * license * fix * fix * fix readme * fix some bugs * remove tokenizer config	10 months ago
yuehuayingxueluo	6fb4bcbb24	[Inference/opt] Fused KVCahce Memcopy (#5374) ... * fused kv memcopy * add TODO in test_kvcache_copy.py	10 months ago
Frank Lee	58740b5f68	[inference] added inference template (#5375)	10 months ago
Frank Lee	8106ede07f	Revert "[Inference] Adapt to Fused rotary (#5348)" (#5373) ... This reverts commit 9f4ab2eb92.	10 months ago
Jianghai	9f4ab2eb92	[Inference] Adapt to Fused rotary (#5348) ... * revise rotary embedding * remove useless print * adapt * fix * add * fix * modeling * fix * fix * fix	10 months ago
yuehuayingxueluo	35382a7fbf	[Inference]Fused the gate and up proj in mlp，and optimized the autograd process. (#5365) ... * fused the gate and up proj in mlp * fix code styles * opt auto_grad * rollback test_inference_engine.py * modifications based on the review feedback. * fix bugs in flash attn * Change reshape to view * fix test_rmsnorm_triton.py	10 months ago
Hongxin Liu	084c91246c	[llama] fix memory issue (#5371) ... * [llama] fix memory issue * [llama] add comment	10 months ago
Yuanheng Zhao	1dedb57747	[Fix/Infer] Remove unused deps and revise requirements (#5341) ... * remove flash-attn dep * rm padding llama * revise infer requirements * move requirements out of module	10 months ago
Hongxin Liu	c53ddda88f	[lr-scheduler] fix load state dict and add test (#5369)	10 months ago
Hongxin Liu	eb4f2d90f9	[llama] polish training script and fix optim ckpt (#5368)	10 months ago
Camille Zhong	a5756a8720	[eval] update llama npu eval (#5366)	10 months ago
Camille Zhong	44ca61a22b	[llama] fix neftune & pbar with start_step (#5364)	10 months ago
Hongxin Liu	a4cec1715b	[llama] add flash attn patch for npu (#5362)	10 months ago
Hongxin Liu	73f9f23fc6	[llama] update training script (#5360) ... * [llama] update training script * [doc] polish docstr	10 months ago
Hongxin Liu	6c0fa7b9a8	[llama] fix dataloader for hybrid parallel (#5358) ... * [plugin] refactor prepare dataloader * [plugin] update train script	10 months ago
Hongxin Liu	2dd01e3a14	[gemini] fix param op hook when output is tuple (#5355) ... * [gemini] fix param op hook when output is tuple * [gemini] fix param op hook	10 months ago
yuehuayingxueluo	631862f339	[Inference]Optimize generation process of inference engine (#5356) ... * opt inference engine * fix run_benchmark.sh * fix generate in engine.py * rollback tesh_inference_engine.py	10 months ago
yuehuayingxueluo	21ad4a27f9	[Inference/opt]Optimize the mid tensor of RMS Norm (#5350) ... * opt rms_norm * fix bugs in rms_layernorm	10 months ago
Wenhao Chen	1c790c0877	[fix] remove unnecessary dp_size assert (#5351) ... * fix: remove unnecessary assert * test: add more 3d plugin tests * fix: add warning	10 months ago
Frank Lee	027aa1043f	[doc] updated inference readme (#5343)	10 months ago
Frank Lee	e76acbb076	[inference] moved ops tests to test_infer (#5354)	10 months ago
Frank Lee	db1a763307	[inference] removed redundancy init_batch (#5353)	10 months ago
Hongxin Liu	ffffc32dc7	[checkpointio] fix gemini and hybrid parallel optim checkpoint (#5347) ... * [checkpointio] fix hybrid parallel optim checkpoint * [extension] fix cuda extension * [checkpointio] fix gemini optimizer checkpoint * polish code	10 months ago
yuehuayingxueluo	249644c23b	[Inference]Repalce Attention layer and MLP layer by shardformer to optimize the weight transpose operation，add fused_qkv and fused linear_add (#5340) ... * add fused qkv * replace attn and mlp by shardformer * fix bugs in mlp * add docstrings * fix test_inference_engine.py * add optimize unbind * add fused_addmm * rm squeeze(1) * refactor codes * fix ci bugs * rename ShardFormerLlamaMLP and ShardFormerLlamaAttention * Removed the dependency on LlamaFlashAttention2 * rollback test_inference_engine.py	10 months ago
Frank Lee	f8e456d202	[inference] simplified config verification (#5346) ... * [inference] simplified config verification * polish * polish	10 months ago
YeAnbang	c5239840e6	[Chat] fix sft loss nan (#5345) ... * fix script * fix script * fix chat nan * fix chat nan	10 months ago
Frank Lee	abd8e77ad8	[extension] fixed exception catch (#5342)	10 months ago
Jianghai	df0aa49585	[Inference] Kernel Fusion, fused copy kv cache into rotary embedding (#5336) ... * revise rotary embedding * remove useless print * adapt	10 months ago
Frank Lee	1336838a91	Merge pull request #5339 from FrankLeeeee/sync/merge-main ... Sync/merge main	10 months ago
FrankLeeeee	c565519913	merge commit	10 months ago
Yuanheng Zhao	5f98a9d68a	[Infer] Optimize Blocked KVCache And Kernels Using It (#5325) ... * revise shape of kvcache (context attn kernel) * revise shape of kvcache (flash decoding kernel) * revise shape of kvcache (kvcache copy) and attn func * init of kvcache in kvcache manager * revise llama modeling * revise block size retrieval * use torch for rms_norm benchmarking * revise block size retrieval	10 months ago