3257 Commits (feat/online-serving)

 

All Branches   

Search

Author	SHA1	Message	Date
digger yu	bce9499ed3	fix some typo (#5307)	10 months ago
李文军	ec912b1ba9	[NFC] polish applications/Colossal-LLaMA-2/colossal_llama2/tokenizer/init_tokenizer.py code style (#5228)	10 months ago
Yuanheng Zhao	af8359c430	[hotfix] fix boundary check in batch (#5306)	10 months ago
Jianghai	c647e00e3c	[Inference]Add fused rotary kernel and get cos cache kernel (#5302) ... * add fused rotary and get cos cache func * staged * fix bugs * fix bugs	10 months ago
Yuanheng Zhao	3da9993b0d	[Kernel/Fix] Revise flash attention triton kernel API and add benchmark (#5301) ... * fix decoding kernel pytest * revise and add triton context attn benchmark	10 months ago
Jianghai	8e606ecc7e	[Inference] Benchmarking rotary embedding and add a fetch function (#5277) ... * fix bugs and add a cos/sin cache fetch func * add docstring * fix bug * fix	10 months ago
Desperado-Jia	ddf879e2db	fix bug for mefture (#5299)	10 months ago
yuehuayingxueluo	b7853196a0	Merge pull request #5297 from yuehuayingxueluo/fix_rotary_embedding ... [Inference/fix]Add utils.py for Rotary Embedding	10 months ago
yuehuayingxueluo	cea9c86e45	add utils.py	10 months ago
Hongxin Liu	d7f8db8e21	[hotfix] fix 3d plugin test (#5292)	10 months ago
yuehuayingxueluo	bfff9254ac	[inference] Adapted to Rotary Embedding and RMS Norm (#5283) ... * adapted to rotary_embedding * adapted to nopad rms norm * fix bugs in benchmark * fix flash_decoding.py	10 months ago
flybird11111	f7e3f82a7e	fix llama pretrain (#5287)	10 months ago
Desperado-Jia	6a56967855	[doc] add llama2-13B disyplay (#5285) ... * Update README.md * fix 13b typo --------- Co-authored-by: binmakeswell <binmakeswell@gmail.com>	10 months ago
Yuanheng Zhao	6e487e7d3c	[kernel/fix] Performance Optimization for Decoding Kernel and Benchmarking (#5274) ... * prevent re-creating intermediate tensors * add singleton class holding intermediate values * fix triton kernel api * add benchmark in pytest * fix kernel api and add benchmark * revise flash decoding triton kernel in/out shapes * fix calling of triton kernel in modeling * fix pytest: extract to util functions	10 months ago
Jianghai	9e2342bde2	[Hotfix] Fix bugs in testing continuous batching (#5270) ... * fix bug * fix bugs * fix bugs * fix bugs and add padding * add funcs and fix bugs * fix typos * fix bugs * add func	10 months ago
Michelle	32cb74493a	fix auto loading gpt2 tokenizer (#5279)	10 months ago
Frank Lee	d66e6988bc	Merge pull request #5278 from ver217/sync/npu ... [sync] sync npu branch with main	10 months ago
ver217	148469348a	Merge branch 'main' into sync/npu	10 months ago
Yaozheng Fang	5ae9099f92	[kernel] Add RMSLayerNorm triton kernel (#5262) ... * add layerrmsnorm triton kernel * add layerrmsnorm kernel * modify the atol and rtol in test file * Remove the logics of mean computations, and update the name of ther kernel functions and files * add benchmark of rms norm	10 months ago
Zhongkai Zhao	5d9a0ae75b	[hotfix] Fix ShardFormer test execution path when using sequence parallelism (#5230)	10 months ago
yuehuayingxueluo	86b63f720c	[Inference]Adapted to the triton attn kernels (#5264) ... * adapted to the triton attn kernels * fix pad input * adapted to copy_kv_to_blocked_cache * fix ci test * update kv memcpy * remove print	10 months ago
flybird11111	46e091651b	[shardformer] hybridparallelplugin support gradients accumulation. (#5246) ... * support gradients acc fix fix fix fix fix fix fix fix fix fix fix fix fix * fix fix * fix fix fix	10 months ago
flybird11111	2a0558d8ec	[ci] fix test_hybrid_parallel_plugin_checkpoint_io.py (#5276) ... * fix ci fix * fix test * revert: revert p2p * feat: add enable_metadata_cache option * revert: enable t5 tests * fix --------- Co-authored-by: Wenhao Chen <cwher@outlook.com>	10 months ago
Frank Lee	d69cd2eb89	[workflow] fixed oom tests (#5275) ... * [workflow] fixed oom tests * polish * polish * polish	10 months ago
Yuanheng Zhao	0f2b46a41c	[kernel] Revise KVCache copy triton kernel API (#5273) ... * [kernel/fix] revise kvcache copy kernel api * fix benchmark	10 months ago
Frank Lee	04244aaaf1	[workflow] fixed incomplete bash command (#5272)	10 months ago
Jianghai	d8db500efc	[Inference] Fix request handler and add recycle logic (#5260) ... * fix request handler * fix comment	10 months ago
Frank Lee	c597678da4	[doc] updated inference readme (#5269)	10 months ago
Yuanheng Zhao	fa85e02b3b	[kernel] Add KV cache copy kernel during decoding (#5261) ... * add kv copy triton kernel during decoding stage * add pytest and fix kernel * fix test utilities * revise kernel config * add benchmark for kvcache copy	10 months ago
Wenhao Chen	ef4f0ee854	[hotfix]: add pp sanity check and fix mbs arg (#5268) ... * fix: fix misleading mbs arg * feat: add pp sanity check * fix: fix 1f1b sanity check	10 months ago
FrankLeeeee	1ded7e81ef	[git] fixed rebased files	11 months ago
Yuanheng Zhao	1513f20f4d	[kernel] Add flash decoding triton kernel for blocked kv cache (#5249) ... * add flash decoding unpad triton kernel * rename flash decoding kernel * add kernel testing (draft) * revise pytest * support kv group (GQA) * (trivial) fix api and pytest * (trivial) func renaming * (trivial) func/file renaming * refactor pytest for attention * (trivial) format and consistent vars of context/decode attn * (trivial) remove test redundancy	11 months ago
Jianghai	fded91d049	[Inference] Kernel: no pad rotary embedding (#5252) ... * fix bugs * comment * use more accurate atol * fix	11 months ago
yuehuayingxueluo	d40eb26029	fix bugs in request_handler.py and engine.py	11 months ago
yuehuayingxueluo	10e3c9f923	rm torch.cuda.synchronize	11 months ago
yuehuayingxueluo	fab294c7f4	fix CI bugs	11 months ago
yuehuayingxueluo	2a73e828eb	fix bugs related to processing padding mask	11 months ago
Jianghai	e545a871b8	[Hotfix] Fix accuracy and align attention method api with Triton kernel (#5229) ... * fix accuracy * alignment in attention * fix attention * fix * fix bugs * fix bugs * fix bugs	11 months ago
yuehuayingxueluo	fa4fbdbffb	adapted to pad_context_forward	11 months ago
yuehuayingxueluo	47e53eaa1c	fix bugs in attention.py and request_handler.py	11 months ago
Jianghai	bfd9b1b494	[Inference] Pytorch Attention func, pad&nopad input support (#5219) ... * add attn * add attention test * fix attn forward * fix decoding	11 months ago
yuehuayingxueluo	3ad1f3b78b	fix beam_width	11 months ago
yuehuayingxueluo	b2eb9cd186	Fixed a typo	11 months ago
yuehuayingxueluo	bbfebfb9fc	fix bugs in sampler	11 months ago
yuehuayingxueluo	02c1bf8b2a	add context_attention_unpadded	11 months ago
Yuanheng Zhao	07b5283b6a	[kernel] Add triton kernel for context attention (FAv2) without padding (#5192) ... * add context attn unpadded triton kernel * test compatibility * kv cache copy (testing) * fix k/v cache copy * fix kv cache copy and test * fix boundary of block ptrs * add support for GQA/MQA and testing * fix import statement --------- Co-authored-by: Round Heng <yuanhengzhao@Rounds-MacBook-Pro.local>	11 months ago
yuehuayingxueluo	4df8876fca	Fixed a writing error	11 months ago
yuehuayingxueluo	9489dc64d8	precision alignment	11 months ago
yuehuayingxueluo	62968588d1	fix bugs in request_handler	11 months ago
yuehuayingxueluo	62fd08ee44	Fixed a bug in the inference frame	11 months ago