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>
3 months ago
7c2f79fa98
[pre-commit.ci] pre-commit autoupdate ( #5572 )
...
* [pre-commit.ci] pre-commit autoupdate
updates:
- [github.com/PyCQA/autoflake: v2.2.1 → v2.3.1](https://github.com/PyCQA/autoflake/compare/v2.2.1...v2.3.1 )
- [github.com/pycqa/isort: 5.12.0 → 5.13.2](https://github.com/pycqa/isort/compare/5.12.0...5.13.2 )
- [github.com/psf/black-pre-commit-mirror: 23.9.1 → 24.4.2](https://github.com/psf/black-pre-commit-mirror/compare/23.9.1...24.4.2 )
- [github.com/pre-commit/mirrors-clang-format: v13.0.1 → v18.1.7](https://github.com/pre-commit/mirrors-clang-format/compare/v13.0.1...v18.1.7 )
- [github.com/pre-commit/pre-commit-hooks: v4.3.0 → v4.6.0](https://github.com/pre-commit/pre-commit-hooks/compare/v4.3.0...v4.6.0 )
* [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>
5 months ago
a1e39f4c0d
[install]fix setup ( #5786 )
...
* fix
* [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
c46e09715c
Allow building cuda extension without a device. ( #5535 )
...
Added FORCE_CUDA environment variable support, to enable building extensions where a GPU device is not present but cuda libraries are.
6 months ago
121d7ad629
[Inference] Delete duplicated copy_vector ( #5716 )
7 months ago
7806842f2d
add paged-attetionv2: support seq length split across thread block ( #5707 )
7 months ago
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
7 months ago
1ace1065e6
[Inference/Feat] Add quant kvcache support for decode_kv_cache_memcpy ( #5686 )
7 months ago
725fbd2ed0
[Inference] Remove unnecessary float4_ and rename float8_ to float8 ( #5679 )
7 months ago
9df016fc45
[Inference] Fix quant bits order ( #5681 )
7 months ago
ef8e4ffe31
[Inference/Feat] Add kvcache quant support for fused_rotary_embedding_cache_copy ( #5680 )
7 months ago
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
7 months ago
808ee6e4ad
[Inference/Feat] Feat quant kvcache step2 ( #5674 )
7 months ago
8ccb6714e7
[Inference/Feat] Add kvcache quantization support for FlashDecoding ( #5656 )
7 months ago
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>
7 months ago
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
7 months ago
12f10d5b0b
[Fix/Inference]Fix CUDA Rotary Rmbedding GQA ( #5623 )
...
* fix rotary embedding GQA
* change test_rotary_embdding_unpad.py KH
7 months ago
ccf72797e3
feat baichuan2 rmsnorm whose hidden size equals to 5120 ( #5611 )
7 months ago
be396ad6cc
[Inference/Kernel] Add Paged Decoding kernel, sequence split within the same thread block ( #5531 )
...
* feat flash decoding for paged attention
* refactor flashdecodingattention
* [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>
7 months ago
d4cb023b62
[Inference/Refactor] Delete Duplicated code and refactor vec_copy utils and reduce utils ( #5593 )
...
* delete duplicated code and refactor vec_copy utils and reduce utils
* delete unused header file
8 months ago
a21912339a
refactor csrc ( #5582 )
8 months ago
d78817539e
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
8 months ago
ed5ebd1735
[Fix] resolve conflicts of merging main
8 months ago
641b1ee71a
[devops] remove post commit ci ( #5566 )
...
* [devops] remove post commit ci
* [misc] run pre-commit on all files
* [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>
8 months ago
7ebdf48ac5
add cast and op_functor for cuda build-in types ( #5546 )
8 months ago
a2878e39f4
[Inference] Add Reduce Utils ( #5537 )
...
* add reduce utils
* add using to delele namespace prefix
8 months ago
04aca9e55b
[Inference/Kernel]Add get_cos_and_sin Kernel ( #5528 )
...
* Add get_cos_and_sin kernel
* fix code comments
* fix code typos
* merge common codes of get_cos_and_sin kernel.
* Fixed a typo
* Changed 'asset allclose' to 'assert equal'.
8 months ago
934e31afb2
The writing style of tail processing and the logic related to macro definitions have been optimized. ( #5519 )
8 months ago
19e1a5cf16
[shardformer] update colo attention to support custom mask ( #5510 )
...
* [feature] refactor colo attention (#5462 )
* [extension] update api
* [feature] add colo attention
* [feature] update sdpa
* [feature] update npu attention
* [feature] update flash-attn
* [test] add flash attn test
* [test] update flash attn test
* [shardformer] update modeling to fit colo attention (#5465 )
* [misc] refactor folder structure
* [shardformer] update llama flash-attn
* [shardformer] fix llama policy
* [devops] update tensornvme install
* [test] update llama test
* [shardformer] update colo attn kernel dispatch
* [shardformer] update blip2
* [shardformer] update chatglm
* [shardformer] update gpt2
* [shardformer] update gptj
* [shardformer] update opt
* [shardformer] update vit
* [shardformer] update colo attention mask prep
* [shardformer] update whisper
* [test] fix shardformer tests (#5514 )
* [test] fix shardformer tests
* [test] fix shardformer tests
8 months ago
87079cffe8
[Inference]Support FP16/BF16 Flash Attention 2 And Add high_precision Flag To Rotary Embedding ( #5461 )
...
* Support FP16/BF16 Flash Attention 2
* fix bugs in test_kv_cache_memcpy.py
* add context_kv_cache_memcpy_kernel.cu
* rm typename MT
* add tail process
* add high_precision
* add high_precision to config.py
* rm unused code
* change the comment for the high_precision parameter
* update test_rotary_embdding_unpad.py
* fix vector_copy_utils.h
* add comment for self.high_precision when using float32
8 months ago
7ff42cc06d
add vec_type_trait implementation ( #5473 )
8 months ago
48c4f29b27
refactor vector utils
8 months ago
5724b9e31e
add some comments
9 months ago
388e043930
add implementatino for GetGPULaunchConfig1D
9 months ago
f366a5ea1f
[Inference/kernel]Add Fused Rotary Embedding and KVCache Memcopy CUDA Kernel ( #5418 )
...
* add rotary embedding kernel
* add rotary_embedding_kernel
* add fused rotary_emb and kvcache memcopy
* add fused_rotary_emb_and_cache_kernel.cu
* add fused_rotary_emb_and_memcopy
* fix bugs in fused_rotary_emb_and_cache_kernel.cu
* fix ci bugs
* use vec memcopy and opt the gloabl memory access
* fix code style
* fix test_rotary_embdding_unpad.py
* codes revised based on the review comments
* fix bugs about include path
* rm inline
9 months ago
ed431de4e4
fix rmsnorm template function invocation problem(template function partial specialization is not allowed in Cpp) and luckily pass e2e precision test ( #5454 )
9 months ago
c1c45e9d8e
fix include path
9 months ago
b699f54007
optimize rmsnorm: add vectorized elementwise op, feat loop unrolling ( #5441 )
9 months ago
095c070a6e
refactor code
9 months ago
21e1e3645c
Merge pull request #5435 from Courtesy-Xs/add_gpu_launch_config
...
Add query and other components
9 months ago
f7aecc0c6b
feat rmsnorm cuda kernel and add unittest, benchmark script ( #5417 )
9 months ago
5eb5ff1464
refactor code
9 months ago
01d289d8e5
Merge branch 'feature/colossal-infer' of https://github.com/hpcaitech/ColossalAI into add_gpu_launch_config
9 months ago
a46598ac59
add reusable utils for cuda
9 months ago
95c21498d4
add silu_and_mul for infer
9 months ago
070df689e6
[devops] fix extention building ( #5427 )
9 months ago
0310b76e9d
Merge branch 'main' into sync/main
9 months ago
600881a8ea
[Inference]Add CUDA KVCache Kernel ( #5406 )
...
* add cuda KVCache kernel
* annotation benchmark_kvcache_copy
* add use cuda
* fix import path
* move benchmark scripts to example/
* rm benchmark codes in test_kv_cache_memcpy.py
* rm redundancy codes
* rm redundancy codes
* pr was modified according to the review
9 months ago
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
abd8e77ad8
[extension] fixed exception catch ( #5342 )
10 months ago
Edenzzzz