ColossalAI

Commit Graph

Author	SHA1	Message	Date
botbw	3bcbba9262	[gemini] quick fix on possible async operation (#5803 ) * [gemini] quick fix on possible async operation * [gemini] quick fix on possible async operation	5 months ago
Haze188	d9dddf574f	[Gemini] Use async stream to prefetch and h2d data moving (#5781 ) * use async stream to prefetch and h2d data moving * Remove redundant code	5 months ago
Li Xingjian	8554585a5f	[Inference] Fix flash-attn import and add model test (#5794 ) * Fix torch int32 dtype Signed-off-by: char-1ee <xingjianli59@gmail.com> * Fix flash-attn import Signed-off-by: char-1ee <xingjianli59@gmail.com> * Add generalized model test Signed-off-by: char-1ee <xingjianli59@gmail.com> * Remove exposed path to model Signed-off-by: char-1ee <xingjianli59@gmail.com> * Add default value for use_flash_attn Signed-off-by: char-1ee <xingjianli59@gmail.com> * Rename model test Signed-off-by: char-1ee <xingjianli59@gmail.com> --------- Signed-off-by: char-1ee <xingjianli59@gmail.com>	5 months ago
Hongxin Liu	aa125bcc91	[shardformer] fix modeling of bloom and falcon (#5796 )	5 months ago
Runyu Lu	c0948aff97	[Inference]refactor baichuan (#5791 ) * refactor baichuan * remove unused code and add TODO for lazyinit	5 months ago
char-1ee	f5981e808e	Remove flash attention backend Signed-off-by: char-1ee <xingjianli59@gmail.com>	6 months ago
char-1ee	ceba662d22	Clean up Signed-off-by: char-1ee <xingjianli59@gmail.com>	6 months ago
char-1ee	5f398fc000	Pass inference model shard configs for module init Signed-off-by: char-1ee <xingjianli59@gmail.com>	6 months ago
char-1ee	eec77e5702	Fix tests and naming Signed-off-by: char-1ee <xingjianli59@gmail.com>	6 months ago
char-1ee	04386d9eff	Refactor modeling by adding attention backend Signed-off-by: char-1ee <xingjianli59@gmail.com>	6 months ago
Hongxin Liu	73e88a5553	[shardformer] fix import (#5788 )	6 months ago
Hongxin Liu	b9d646fe9e	[misc] fix dist logger (#5782 )	6 months ago
botbw	3f7e3131d9	[gemini] optimize reduce scatter d2h copy (#5760 ) * [gemini] optimize reduce scatter d2h copy * [fix] fix missing reduce variable * [refactor] remove legacy async reduce scatter code * [gemini] missing sync * Revert "[refactor] remove legacy async reduce scatter code" This reverts commit `58ad76d466`. * [gemini] further optimize with async all reduce * [fix] pass flag from manager to chunk	6 months ago
Edenzzzz	79f7a7b211	[misc] Accelerate CI for zero and dist optim (#5758 ) * remove fp16 from lamb * remove d2h copy in checking states --------- Co-authored-by: Edenzzzz <wtan45@wisc.edu>	6 months ago
flybird11111	50b4c8e8cf	[hotfix] fix llama flash attention forward (#5777 )	6 months ago
yuehuayingxueluo	b45000f839	[Inference]Add Streaming LLM (#5745 ) * Add Streaming LLM * add some parameters to llama_generation.py * verify streamingllm config * add test_streamingllm.py * modified according to the opinions of review * add Citation * change _block_tables tolist	6 months ago
Yuanheng Zhao	406443200f	[Hotfix] Add missing init file in inference.executor (#5774 )	6 months ago
duanjunwen	1b76564e16	[test] Fix/fix testcase (#5770 ) * [fix] branch for fix testcase; * [fix] fix test_analyzer & test_auto_parallel; * [fix] remove local change about moe; * [fix] rm local change moe;	6 months ago
flybird11111	3f2be80530	fix (#5765 )	6 months ago
hxwang	8547562884	[chore] remove unnecessary assert since compute list might not be recorded	6 months ago
hxwang	e5e3320948	[bug] continue fix	6 months ago
hxwang	936dd96dbb	[bug] workaround for idx fix	6 months ago
Edenzzzz	5f8c0a0ac3	[Feature] auto-cast optimizers to distributed version (#5746 ) * auto-cast optimizers to distributed * fix galore casting * logger --------- Co-authored-by: Edenzzzz <wtan45@wisc.edu>	6 months ago
botbw	2fc85abf43	[gemini] async grad chunk reduce (all-reduce&reduce-scatter) (#5713 ) * [gemini] async grad chunk reduce (all-reduce&reduce-scatter) * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * [gemini] add test * [gemini] rename func * [gemini] update llama benchmark * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * [gemini] use tensor counter * [gemini] change default config in GeminiPlugin and GeminiDDP * [chore] typo * [gemini] fix sync issue & add test cases * [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>	6 months ago
Jianghai	85946d4236	[Inference]Fix readme and example for API server (#5742 ) * fix chatapi readme and example * updating doc * add an api and change the doc * remove * add credits and del 'API' heading * readme * readme	6 months ago
binmakeswell	4647ec28c8	[inference] release (#5747 ) * [inference] release * [inference] release * [inference] release * [inference] release * [inference] release * [inference] release * [inference] release	6 months ago
Yuanheng Zhao	bd38fe6b91	[NFC] Fix code factors on inference triton kernels (#5743 )	6 months ago
botbw	13c06d36a3	[bug] fix early return (#5740 ) * [bug] fix silly bug * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * [chore] add test for prefetch * [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>	6 months ago
Haze188	22ce873c3f	[Shardformer] Add parallel output for shardformer models(bloom, falcon) (#5702 ) * [pre-commit.ci] auto fixes from pre-commit.com hooks * add parallel cross entropy output for falcon model & fix some typos in bloom.py * fix module name error, self.model -> self.transformers in bloom, falcon model * Fix the overflow bug of distributed cross entropy loss function when training with fp16 * add dtype to parallel cross entropy loss function * fix dtype related typos adn prettify the loss.py * fix grad dtype and update dtype mismatch error * fix typo bugs	6 months ago
pre-commit-ci[bot]	b3c0e6d871	[pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci	6 months ago
hxwang	137a7c341b	[chore] fix init error	6 months ago
Yuanheng Zhao	d8b1ea4ac9	[doc] Update Inference Readme (#5736 ) * [doc] update inference readme * add contents * trivial	6 months ago
Yuanheng Zhao	bdf9a001d6	[Fix/Inference] Add unsupported auto-policy error message (#5730 ) * [fix] auto policy error message * trivial	6 months ago
genghaozhe	90d8d0183c	remove personal comments	6 months ago
genghaozhe	bfcb2d1ff8	refactor the code structure to solve the circular import	6 months ago
genghaozhe	1ec92d29af	remove perf log, unrelated file and so on	6 months ago
genghaozhe	5c6c5d6be3	remove comments	6 months ago
genghaozhe	df63db7e63	remote comments	6 months ago
genghaozhe	d22bf30ca6	implement auto policy prefetch and modify a little origin code.	6 months ago
pre-commit-ci[bot]	f1918e18a5	[pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci	6 months ago
hxwang	a55a9e298b	[gemini] init auto policy prefetch	6 months ago
Yuanheng Zhao	283c407a19	[Inference] Fix Inference Generation Config and Sampling (#5710 ) * refactor and add * config default values * fix gen config passing * fix rpc generation config	6 months ago
genghaozhe	06a3a100b3	remove unrelated code	6 months ago
genghaozhe	3d625ca836	add some todo Message	6 months ago
flybird11111	9d83c6d715	[lazy] fix lazy cls init (#5720 ) * fix * fix * fix * fix * fix * remove kernel intall * rebase revert fix * fix * fix	6 months ago
botbw	e57812c672	[chore] Update placement_policy.py	6 months ago
Yuanheng Zhao	8bcfe360fd	[example] Update Inference Example (#5725 ) * [example] update inference example	6 months ago
genghaozhe	013690a86b	remove set(all_chunks)	6 months ago
hxwang	6efbadba25	[chore] remove debugging info	6 months ago
hxwang	20701d4533	[chore] remove print	6 months ago

1 2 3 4 5 ...

2088 Commits (f5c84af0b01bcd2e993d38dc628793f7f0a8ba64)