Aaron Pham
9d104b5beb
[CI/Build] Update Ruff version ( #8469 )
...
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2024-09-18 11:00:56 +00:00
Kevin Lin
5faedf1b62
[Spec Decode] Move ops.advance_step to flash attn advance_step ( #8224 )
2024-09-10 13:18:14 -07:00
Lily Liu
e6a26ed037
[SpecDecode][Kernel] Flashinfer Rejection Sampling ( #7244 )
2024-09-01 21:23:29 -07:00
afeldman-nm
428dd1445e
[Core] Logprobs support in Multi-step ( #7652 )
2024-08-29 19:19:08 -07:00
Jonas M. Kübler
f205c09854
[Bugfix] Unify rank computation across regular decoding and speculative decoding ( #7899 )
2024-08-28 22:18:13 -07:00
Nick Hill
1856aff4d6
[Spec Decoding] Streamline batch expansion tensor manipulation ( #7851 )
2024-08-25 15:45:14 -07:00
Travis Johnson
cc0eaf12b1
[Bugfix] spec decode handle None entries in topk args in create_sequence_group_output ( #7232 )
...
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
2024-08-22 09:33:48 -04:00
Abhinav Goyal
a3fce56b88
[Speculative Decoding] EAGLE Implementation with Top-1 proposer ( #6830 )
2024-08-22 02:42:24 -07:00
Antoni Baum
3b682179dd
[Core] Add AttentionState abstraction ( #7663 )
2024-08-20 18:50:45 +00:00
Abhinav Goyal
312f761232
[Speculative Decoding] Fixing hidden states handling in batch expansion ( #7508 )
2024-08-19 17:58:14 -07:00
SangBin Cho
ff7ec82c4d
[Core] Optimize SPMD architecture with delta + serialization optimization ( #7109 )
2024-08-18 17:57:20 -07:00
Roger Wang
bbf55c4805
[VLM] Refactor MultiModalConfig initialization and profiling ( #7530 )
2024-08-17 13:30:55 -07:00
William Lin
f366f6339b
[spec decode] [4/N] Move update_flash_attn_metadata to attn backend ( #7571 )
...
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
2024-08-16 11:41:56 -07:00
Mahesh Keralapura
933790c209
[Core] Add span metrics for model_forward, scheduler and sampler time ( #7089 )
2024-08-09 13:55:13 -07:00
William Lin
57b7be0e1c
[Speculative decoding] [Multi-Step] decouple should_modify_greedy_probs_inplace ( #6971 )
2024-08-09 05:42:45 +00:00
Bongwon Jang
e9630458c7
[SpecDecode] Support FlashInfer in DraftModelRunner ( #6926 )
2024-08-05 08:05:05 -07:00
Cade Daniel
82a1b1a82b
[Speculative decoding] Add periodic log with time spent in proposal/scoring/verification ( #6963 )
2024-08-05 08:46:44 +00:00
Cyrus Leung
f230cc2ca6
[Bugfix] Fix broadcasting logic for multi_modal_kwargs ( #6836 )
2024-07-31 10:38:45 +08:00
Nick Hill
5cf9254a9c
[BugFix] Fix use of per-request seed with pipeline parallel ( #6698 )
2024-07-30 10:40:08 -07:00
Allen.Dou
40468b13fa
[Bugfix] Miscalculated latency lead to time_to_first_token_seconds inaccurate. ( #6686 )
2024-07-24 08:58:42 -07:00
sroy745
14f91fe67c
[Spec Decode] Disable Log Prob serialization to CPU for spec decoding for both draft and target models. ( #6485 )
2024-07-20 23:58:58 -07:00
Matt Wong
06d6c5fe9f
[Bugfix][CI/Build][Hardware][AMD] Fix AMD tests, add HF cache, update CK FA, add partially supported model notes ( #6543 )
2024-07-20 09:39:07 -07:00
Thomas Parnell
f0bbfaf917
[Bugfix] [SpecDecode] AsyncMetricsCollector: update time since last collection ( #6578 )
2024-07-19 14:01:03 -07:00
Woo-Yeon Lee
a921e86392
[BUGFIX] Raise an error for no draft token case when draft_tp>1 ( #6369 )
2024-07-19 06:01:09 -07:00
Thomas Parnell
d4201e06d5
[Bugfix] Make spec. decode respect per-request seed. ( #6034 )
...
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2024-07-18 19:22:08 -07:00
Cody Yu
8a74c68bd1
[Misc] Minor patch for draft model runner ( #6523 )
2024-07-18 06:06:21 +00:00
Alexander Matveev
e76466dde2
[Core] draft_model_runner: Implement prepare_inputs on GPU for advance_step ( #6338 )
2024-07-17 14:30:28 -07:00
shangmingc
a19e8d3726
[Misc][Speculative decoding] Typos and typing fixes ( #6467 )
...
Co-authored-by: caishangming.csm <caishangming.csm@alibaba-inc.com>
2024-07-17 07:17:07 +00:00
sroy745
ae151d73be
[Speculative Decoding] Enabling bonus token in speculative decoding for KV cache based models ( #5765 )
2024-07-10 16:02:47 -07:00
Abhinav Goyal
2416b26e11
[Speculative Decoding] Medusa Implementation with Top-1 proposer ( #4978 )
2024-07-09 18:34:02 -07:00
Swapnil Parekh
4d6ada947c
[CORE] Adding support for insertion of soft-tuned prompts ( #4645 )
...
Co-authored-by: Swapnil Parekh <swapnilp@ibm.com>
Co-authored-by: Joe G <joseph.granados@h2o.ai>
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>
2024-07-09 13:26:36 -07:00
xwjiang2010
d9e98f42e4
[vlm] Remove vision language config. ( #6089 )
...
Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
2024-07-03 22:14:16 +00:00
Mor Zusman
9d6a8daa87
[Model] Jamba support ( #4115 )
...
Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
Co-authored-by: Erez Schwartz <erezs@ai21.com>
Co-authored-by: Mor Zusman <morz@ai21.com>
Co-authored-by: tomeras91 <57313761+tomeras91@users.noreply.github.com>
Co-authored-by: Tomer Asida <tomera@ai21.com>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
Co-authored-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
2024-07-02 23:11:29 +00:00
Murali Andoorveedu
c5832d2ae9
[Core] Pipeline Parallel Support ( #4412 )
...
Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
2024-07-02 10:58:08 -07:00
Sirej Dua
15aba081f3
[Speculative Decoding] MLPSpeculator Tensor Parallel support (1/2) ( #6050 )
...
Co-authored-by: Sirej Dua <sirej.dua@databricks.com>
Co-authored-by: Sirej Dua <Sirej Dua>
2024-07-02 07:20:29 -07:00
sroy745
80ca1e6a3a
[Speculative Decoding 2/2 ] Integrate typical acceptance sampler into Spec Decode Worker ( #5348 )
2024-07-01 00:33:05 -07:00
Cody Yu
b2c620230a
[Spec Decode] Introduce DraftModelRunner ( #5799 )
2024-06-28 09:17:51 -07:00
Stephanie Wang
dda4811591
[Core] Refactor Worker and ModelRunner to consolidate control plane communication ( #5408 )
...
Signed-off-by: Stephanie Wang <swang@cs.berkeley.edu>
Signed-off-by: Stephanie <swang@anyscale.com>
Co-authored-by: Stephanie <swang@anyscale.com>
2024-06-25 20:30:03 -07:00
Woo-Yeon Lee
2ce5d6688b
[Speculative Decoding] Support draft model on different tensor-parallel size than target model ( #5414 )
2024-06-25 09:56:06 +00:00
Joshua Rosenkranz
b12518d3cf
[Model] MLPSpeculator speculative decoding support ( #4947 )
...
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
Co-authored-by: Davis Wertheimer <Davis.Wertheimer@ibm.com>
2024-06-20 20:23:12 -04:00
Cyrus Leung
0e9164b40a
[mypy] Enable type checking for test directory ( #5017 )
2024-06-15 04:45:31 +00:00
Nick Hill
a008629807
[Misc] Various simplifications and typing fixes ( #5368 )
2024-06-11 10:29:02 +08:00
Nick Hill
faf71bcd4b
[Speculative Decoding] Add ProposerWorkerBase abstract class ( #5252 )
2024-06-05 14:53:05 -07:00
Lily Liu
d5a1697772
[Dynamic Spec Decoding] Minor fix for disabling speculative decoding ( #5000 )
2024-05-25 10:00:14 -07:00
Nick Hill
eb6d3c264d
[Core] Eliminate parallel worker per-step task scheduling overhead ( #4894 )
2024-05-23 06:17:27 +09:00
Cody Yu
973617ae02
[Speculative decoding][Re-take] Enable TP>1 speculative decoding ( #4840 )
...
Co-authored-by: Cade Daniel <edacih@gmail.com>
Co-authored-by: Cade Daniel <cade@anyscale.com>
2024-05-16 00:53:51 -07:00
SangBin Cho
65bf2ac165
[Core][2/N] Model runner refactoring part 2. Combine prepare prefill / decode to a single API ( #4681 )
...
This PR combines prepare_prompt and prepare_decode into a single API. This PR also coelsce the attn metadata for prefill/decode to a single class and allow to slice them when running attn backend.
It also refactors subquery_start_loc which was not refactored in the previous PR
2024-05-15 14:00:10 +09:00
Cody Yu
ce532ff45c
[Speculative decoding] Improve n-gram efficiency ( #4724 )
2024-05-13 15:00:13 -07:00
Chang Su
e254497b66
[Model][Misc] Add e5-mistral-7b-instruct and Embedding API ( #3734 )
2024-05-11 11:30:37 -07:00
SangBin Cho
6a0f617210
[Core] Fix circular reference which leaked llm instance in local dev env ( #4737 )
...
Storing exception frame is extremely prone to circular refernece because it contains the reference to objects.
When tensorizer is not installed, it leaks llm instance because error frame has references to various modules which cause circular reference problem.
I also found spec decoding has a circular reference issue, and I solved it using weakref.proxy.
2024-05-10 23:54:32 +09:00
