bcf0181ecd
[Feat] Distrifusion Acceleration Support for Diffusion Inference ( #5895 )
...
* Distrifusion Support source
* comp comm overlap optimization
* sd3 benchmark
* pixart distrifusion bug fix
* sd3 bug fix and benchmark
* generation bug fix
* naming fix
* add docstring, fix counter and shape error
* add reference
* readme and requirement
4 months ago
cba20525a8
[Feat] Diffusion Model(PixArtAlpha/StableDiffusion3) Support ( #5838 )
...
* Diffusion Model Inference support
* Stable Diffusion 3 Support
* pixartalpha support
5 months ago
3c7cda0c9a
[Inference]Lazy Init Support ( #5785 )
...
* lazy init support
* lazy init llama support
* :lazy init support for baichuan
* aligh rpc
* add note for baichuan
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
5 months ago
7b249c76e5
[Fix] Fix spec-dec Glide LlamaModel for compatibility with transformers ( #5837 )
...
* fix glide llama model
* revise
5 months ago
2ddf624a86
[shardformer] upgrade transformers to 4.39.3 ( #5815 )
...
* [shardformer]upgrade transformers for gpt2/gptj/whisper (#5807 )
* [shardformer] fix modeling of gpt2 and gptj
* [shardformer] fix whisper modeling
* [misc] update requirements
---------
Co-authored-by: ver217 <lhx0217@gmail.com>
* [shardformer]upgrade transformers for mistral (#5808 )
* upgrade transformers for mistral
* fix
* fix
* [shardformer]upgrade transformers for llama (#5809 )
* update transformers
fix
* fix
* fix
* [inference] upgrade transformers (#5810 )
* update transformers
fix
* fix
* fix
* fix
* fix
* [gemini] update transformers for gemini (#5814 )
---------
Co-authored-by: ver217 <lhx0217@gmail.com>
5 months ago
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>
6 months ago
c0948aff97
[Inference]refactor baichuan ( #5791 )
...
* refactor baichuan
* remove unused code and add TODO for lazyinit
6 months ago
5f398fc000
Pass inference model shard configs for module init
...
Signed-off-by: char-1ee <xingjianli59@gmail.com>
6 months ago
eec77e5702
Fix tests and naming
...
Signed-off-by: char-1ee <xingjianli59@gmail.com>
6 months ago
04386d9eff
Refactor modeling by adding attention backend
...
Signed-off-by: char-1ee <xingjianli59@gmail.com>
6 months ago
74c47921fa
[Fix] Llama3 Load/Omit CheckpointIO Temporarily ( #5717 )
...
* Fix Llama3 Load error
* Omit Checkpoint IO Temporarily
6 months ago
7806842f2d
add paged-attetionv2: support seq length split across thread block ( #5707 )
6 months ago
8754abae24
[Fix] Fix & Update Inference Tests (compatibility w/ main)
7 months ago
f79963199c
[inference]Add alibi to flash attn function ( #5678 )
...
* add alibi to flash attn function
* rm redundant modifications
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
5f00002e43
[Inference] Adapt Baichuan2-13B TP ( #5659 )
...
* adapt to baichuan2 13B
* add baichuan2 13B TP
* update baichuan tp logic
* rm unused code
* Fix TP logic
* fix alibi slopes tp logic
* rm nn.Module
* Polished the code.
* change BAICHUAN_MODEL_NAME_OR_PATH
* Modified the logic for loading Baichuan weights.
* fix typos
7 months ago
3c91e3f176
[Inference]Adapt to baichuan2 13B ( #5614 )
...
* adapt to baichuan2 13B
* adapt to baichuan2 13B
* change BAICHUAN_MODEL_NAME_OR_PATH
* fix test_decoding_attn.py
* Modifications based on review comments.
* change BAICHUAN_MODEL_NAME_OR_PATH
* mv attn mask processes to test flash decoding
* mv get_alibi_slopes baichuan modeling
* fix bugs in test_baichuan.py
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
5d4c1fe8f5
[Fix/Inference] Fix GQA Triton and Support Llama3 ( #5624 )
...
* [fix] GQA calling of flash decoding triton
* fix kv cache alloc shape
* fix rotary triton - GQA
* fix sequence max length assigning
* Sequence max length logic
* fix scheduling and spec-dec
* skip without import error
* fix pytest - skip without ImportError
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
7 months ago
e37ee2fb65
[Feat]Tensor Model Parallel Support For Inference ( #5563 )
...
* tensor parallel support naive source
* [fix]precision, model load and refactor the framework
* add tp unit test
* docstring
* fix do_sample
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
56b222eff8
[inference/model]Adapted to the baichuan2-7B model ( #5591 )
...
* Adapted to the baichuan2-7B model
* modified according to the review comments.
* Modified the method of obtaining random weights.
* modified according to the review comments.
* change mlp layewr 'NOTE'
7 months ago
f8598e3ec5
[Fix] Llama Modeling Control with Spec-Dec ( #5580 )
...
- fix ref before asgmt
- fall back to use triton kernels when using spec-dec
8 months ago
e60d430cf5
[Fix] resolve conflicts of rebasing feat/speculative-decoding ( #5557 )
...
- resolve conflicts of rebasing feat/speculative-decoding
8 months ago
d85d91435a
[Inference/SpecDec] Support GLIDE Drafter Model ( #5455 )
...
* add glide-llama policy and modeling
* update glide modeling, compitable with transformers 4.36.2
* revise glide llama modeling/usage
* fix issues of glimpsing large kv
* revise the way re-loading params for glide drafter
* fix drafter and engine tests
* enable convert to glide strict=False
* revise glide llama modeling
* revise vicuna prompt template
* revise drafter and tests
* apply usage of glide model in engine
8 months ago
a37f82629d
[Inference/SpecDec] Add Speculative Decoding Implementation ( #5423 )
...
* fix flash decoding mask during verification
* add spec-dec
* add test for spec-dec
* revise drafter init
* remove drafter sampling
* retire past kv in drafter
* (trivial) rename attrs
* (trivial) rename arg
* revise how we enable/disable spec-dec
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
68e9396bc0
[fix] merge conflicts
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
4eafe0c814
[fix] unused option
8 months ago
aabc9fb6aa
[feat] add use_cuda_kernel option
8 months ago
6e30248683
[fix] tmp for test
9 months ago
d02e257abd
Merge branch 'feature/colossal-infer' into colossal-infer-cuda-graph
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
f7aecc0c6b
feat rmsnorm cuda kernel and add unittest, benchmark script ( #5417 )
9 months ago
cefaeb5fdd
[feat] cuda graph support and refactor non-functional api
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
2a718c8be8
Optimized the execution interval time between cuda kernels caused by view and memcopy ( #5390 )
...
* opt_view_and_memcopy
* fix bugs in ci
* fix ci bugs
* update benchmark scripts
* fix ci bugs
9 months ago
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
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
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
6fb4bcbb24
[Inference/opt] Fused KVCahce Memcopy ( #5374 )
...
* fused kv memcopy
* add TODO in test_kvcache_copy.py
10 months ago
8106ede07f
Revert "[Inference] Adapt to Fused rotary ( #5348 )" ( #5373 )
...
This reverts commit 9f4ab2eb92
10 months ago
9f4ab2eb92
[Inference] Adapt to Fused rotary ( #5348 )
...
* revise rotary embedding
* remove useless print
* adapt
* fix
* add
* fix
* modeling
* fix
* fix
* fix
10 months ago
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
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
21ad4a27f9
[Inference/opt]Optimize the mid tensor of RMS Norm ( #5350 )
...
* opt rms_norm
* fix bugs in rms_layernorm
10 months ago
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
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
e8f0642f28
[Inference]Add Nopadding Llama Modeling ( #5327 )
...
* add nopadding llama modeling
* add nopadding_llama.py
* rm unused codes
* fix bugs in test_xine_copy.py
* fix code style
10 months ago
Runyu Lu