93e2ab7111
Disable dynamic speculative decoding when DP is enabled ( #45963 )
...
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-07-07 12:52:41 +00:00
e7c9df9449
[Bugfix][Structured Output][Spec Decode] Constrain bitmask and trim grammar advance at the reasoning boundary ( #44297 )
...
Signed-off-by: Allen.Yu <yuyue0225sc@163.com >
Signed-off-by: yue.yu <yuyue0225sc@163.com >
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com >
2026-07-04 09:08:45 +00:00
07516fda67
[MRV2][SD] Make Dynamic SD comatible with Full Cuda Graphs ( #45953 )
...
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com >
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com >
Co-authored-by: Nick Hill <nickhill123@gmail.com >
2026-07-03 23:58:27 -04:00
3af8789559
[Feature] Universal speculative decoding for heterogeneous vocabularies (TLI) ( #38174 )
...
Signed-off-by: wan-danfeng <wandanfeng0802@gmail.com >
Signed-off-by: Wonderful <wandanfeng0802@gmail.com >
Co-authored-by: Wan_DF <wonderful199082@126.com >
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com >
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com >
2026-07-02 01:34:20 -07:00
Giancarlo Delfin and GitHub
db808b3961
[Model Runner V2][Spec Decode] Implement block verification for rejection sampling ( #46781 )
...
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai >
2026-06-30 08:07:24 -07:00
Benjamin Chislett and GitHub
4c5bc41ba6
[Bugfix][Spec Decode] Fix probabilistic sampling for parallel drafting ( #45956 )
...
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com >
2026-06-24 05:36:23 +00:00
Nick Hill and GitHub
7ee4d22009
[Spec Decode] Reject placeholder (-1) draft tokens in rejection sampler ( #46533 )
...
Signed-off-by: Nick Hill <nickhill123@gmail.com >
2026-06-24 03:32:32 +00:00
44d95069e9
Enable DeepSeek V4 and GLM-5.1 on SM120 ( #43477 )
...
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com >
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com >
2026-06-22 11:54:14 -07:00
Benjamin Chislett and GitHub
89bd2c14d3
[Spec Decode] Add Qwen3 architecture support for EAGLE3 ( #43132 )
...
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com >
2026-06-21 13:55:26 -07:00
stefankoncarevic and GitHub
e2352c2974
[ROCm][Spec Decode] Fix probabilistic draft probs test attention backend ( #45706 )
...
Signed-off-by: Stefan Koncarevic <stefan.koncarevic@amd.com >
2026-06-18 11:59:37 -05:00
4ef4492e9b
[V1][Spec Decode] Add Dynamic SD ( #32374 )
...
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com >
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com >
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com >
2026-06-14 00:14:27 -07:00
ebc6ef971a
Hidden states extraction improvements ( #43805 )
...
Signed-off-by: Fynn Schmitt-Ulms <fschmitt@redhat.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-06-11 09:44:45 -04:00
7fe7800fa4
[BUG] Fix FP64 Gumbel precision coverage ( #43150 )
...
Signed-off-by: tianyu-z <zhangtianyupro@gmail.com >
Signed-off-by: Tianyu Zhang <53099276+tianyu-z@users.noreply.github.com >
Co-authored-by: Nick Hill <nickhill123@gmail.com >
Co-authored-by: OpenAI Codex <codex@openai.com >
2026-06-05 19:04:14 +08:00
Shreyas Kulkarni and GitHub
0eeba5eec1
Fix DFlash prefix cache corruption due to missing lookahead block ( #42971 )
...
Signed-off-by: Shreyas Kulkarni <shreyas.gp269@gmail.com >
2026-06-02 12:06:33 +00:00
fd9e91d7e4
[ROCm][CI] Fix and stabilize EAGLE3 acceptance tests ( #41294 )
...
Signed-off-by: Andreas Karatzas <akaratza@amd.com >
Signed-off-by: Micah Williamson <micah.williamson@amd.com >
Co-authored-by: Micah Williamson <micah.williamson@amd.com >
2026-06-01 12:40:01 -05:00
4e2eba28be
[Perf] Optimize hidden state extraction logic ( #37374 )
...
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com >
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com >
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-05-22 18:23:08 -04:00
Siddharth Bedekar and GitHub
f51f6844f9
[Bugfix][Spec Decode] Wire draft_probs into probabilistic draft_model rejection ( #40269 )
2026-05-13 21:04:03 -04:00
Giancarlo Delfin and GitHub
fe5b4e0fe7
[Model Runner V2] Apply synthetic mode to probabilistic rejection sampler ( #41035 )
2026-05-12 13:37:03 -07:00
shanjiaz and GitHub
6ccb10d794
Added peagle speculators support ( #41826 )
...
Signed-off-by: shanjiaz <zsjwpianpian@gmail.com >
2026-05-12 07:55:57 -07:00
Lucas Wilkinson and GitHub
b1728c1e66
[Attention][Cleanup] Remove tree attention ( #42121 )
...
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com >
2026-05-08 18:36:19 -07:00
Lanze Liu and GitHub
79246b5ea6
[Spec Decode] Fix max_model_len logging in speculative config for draft model ( #41571 )
...
Signed-off-by: Lanze Liu <lanzetech@gmail.com >
2026-05-05 21:56:06 +00:00
wang.yuqi and GitHub
a8208e6a81
[Examples] Resettle features examples. ( #40995 )
...
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io >
2026-04-28 00:33:41 -07:00
Andreas Karatzas and GitHub
428b988c98
[ROCm][CI] Fix trust_remote_code AttributeError in EAGLE3 acceptance length test ( #40306 )
...
Signed-off-by: Andreas Karatzas <akaratza@amd.com >
2026-04-25 02:59:31 +00:00
626daa2076
[Feat] Unified Synthetic Acceptance Rate for V1 and V2 ( #40662 )
...
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com >
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com >
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-04-24 00:48:08 +00:00
Nick Hill and GitHub
fe85a92e86
[Core] Avoid seq_lens_cpu GPU->CPU sync ( #40654 )
...
Signed-off-by: Nick Hill <nickhill123@gmail.com >
2026-04-24 00:35:55 +00:00
Matthew Bonanni and GitHub
cde8d24710
[Spec Decode] Move SpecDecodeBaseProposer out of eagle.py ( #40732 )
...
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com >
2026-04-23 22:28:27 +00:00
zhanqiuhu and GitHub
0b790a2501
[Speculative Decoding] Add DFlash speculators config parsing ( #38300 )
...
Signed-off-by: Zhanqiu Hu <zhu@redhat.com >
2026-04-15 16:22:15 -04:00
0f3ce4c74b
[XPU] Fix spec-decode UTs under tests/v1/spec_decode ( #38491 )
...
Signed-off-by: Yan Ma <yan.ma@intel.com >
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com >
2026-04-11 01:31:00 +00:00
Yan Ma and GitHub
ec68d53b2b
Add platform manual_seed_all API ( #38468 )
...
Signed-off-by: Yan Ma <yan.ma@intel.com >
2026-04-10 13:43:50 +08:00
Giancarlo Delfin and GitHub
5daf62271d
[Model Runner V2] Fuse probabilistic rejection sample kernels ( #38496 )
...
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai >
2026-04-07 17:37:37 -07:00
Aaron Batilo and GitHub
9a528260ef
[Bugfix][Spec Decode] Fix extract_hidden_states for VLM models ( #38987 )
...
Signed-off-by: Aaron Batilo <abatilo@coreweave.com >
2026-04-05 02:41:54 -07:00
wliao2 and GitHub
32e0c0bfa2
refactor hard coded device string in test files under tests/v1 and tests/lora ( #37566 )
...
Signed-off-by: Liao, Wei <wei.liao@intel.com >
2026-04-03 11:21:47 +08:00
757068dc65
[Bugfix][Async] Fix async spec decoding with hybrid models ( #38556 )
...
Signed-off-by: SandishKumarHN <sandishkumarhn@gmail.com >
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com >
Co-authored-by: SandishKumarHN <sandishkumarhn@gmail.com >
2026-03-31 11:08:54 -04:00
Benjamin Chislett and GitHub
494636b29d
[Feat][Spec Decode] DFlash ( #36847 )
...
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com >
2026-03-30 15:03:15 -04:00
Giancarlo Delfin and GitHub
c32e97602d
[Model Runner V2] Enable forcing a specific acceptance rate during rejection sampling ( #38045 )
...
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai >
2026-03-26 13:38:12 -07:00
fafe76b4af
[Async][Spec Decoding] Zero-bubble async scheduling + spec decoding ( #32951 )
...
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com >
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com >
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com >
Co-authored-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com >
Co-authored-by: zhrrr <43847754+izhuhaoran@users.noreply.github.com >
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com >
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com >
2026-03-23 15:37:22 -04:00
Fynn Schmitt-Ulms and GitHub
04bf5a35fa
[Spec Decode] Update extract_hidden_states to use deferred kv_connector clear ( #37013 )
2026-03-16 14:53:45 +01:00
Kunshang Ji and GitHub
53ec16a705
[Hardware] Replace torch.cuda.device_count/current_device/set_device API ( #36145 )
...
Signed-off-by: Kunshang Ji <jikunshang95@gmail.com >
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com >
2026-03-12 07:57:47 -07:00
Sladyn and GitHub
4aaaf8c8ce
feat(spec_decode): fuse EAGLE step slot mapping and metadata updates ( #33503 )
...
Signed-off-by: sladynnunes <snunes@usc.edu >
2026-03-11 04:35:33 +00:00
Matthew Bonanni and GitHub
77a73458e3
Reapply [Attention] Refactor check_and_update_config ( #35122 )
...
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com >
2026-03-09 07:17:14 -07:00
Benjamin Chislett and GitHub
57c629e9c1
[Bugfix] Fix block_size for hybrid model MTP ( #36036 )
...
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com >
2026-03-05 06:10:54 +00:00
28ef9ba399
[BugFix] Add support for MTP num_speculative_tokens > 1 with sparse MLA ( #34552 )
...
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com >
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com >
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com >
2026-03-03 07:21:57 -08:00
Fynn Schmitt-Ulms and GitHub
9433acb8df
[Spec Decode] Add hidden states extraction system ( #33736 )
...
Signed-off-by: Fynn Schmitt-Ulms <fschmitt@redhat.com >
2026-03-02 14:29:09 -05:00
Andreas Karatzas and GitHub
54254f7a61
[ROCm][CI] Fix spec decode logprobs flakiness and parametrize tree attention backends ( #34599 )
...
Signed-off-by: Andreas Karatzas <akaratza@amd.com >
2026-02-20 20:25:23 -08:00
Lucas Wilkinson and GitHub
aaefc58ee0
[CI] Revert PRs 34818 and 33600 ( #34979 )
2026-02-20 13:25:50 -08:00
662205d34e
[Bugfix] Fix Basic Models Test ( #34818 )
...
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com >
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com >
2026-02-19 14:49:07 -08:00
Benjamin Chislett and GitHub
af3162d3aa
[Spec Decode] Unified Parallel Drafting ( #32887 )
...
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com >
2026-02-05 12:37:18 -05:00
shanjiaz and GitHub
d95b4be47a
move spec decode slow test to test_areas.yaml ( #33365 )
...
Signed-off-by: shanjiaz <zsjwpianpian@gmail.com >
2026-02-02 06:28:36 -08:00
shanjiaz and GitHub
5eeba80c74
Adding optional speculator tests for larger models ( #32943 )
...
Signed-off-by: shanjiaz <zsjwpianpian@gmail.com >
2026-01-29 16:54:02 +08:00
a28b94e6ef
[Performance] Split FlashAttn attention and cache update ( #25954 )
...
Signed-off-by: ElizaWszola <ewszola@redhat.com >
Signed-off-by: mgoin <mgoin64@gmail.com >
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com >
Signed-off-by: Luka Govedič <luka.govedic@gmail.com >
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com >
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com >
Signed-off-by: Luka Govedič <lgovedic@redhat.com >
Co-authored-by: mgoin <mgoin64@gmail.com >
Co-authored-by: Varun Sundar Rabindranath <varunsundar08@gmail.com >
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com >
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com >
Co-authored-by: Luka Govedič <luka.govedic@gmail.com >
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com >
Co-authored-by: Luka Govedič <lgovedic@redhat.com >
2026-01-23 17:28:06 -08:00