Commit Graph
133 Commits
Author SHA1 Message Date
Yiliu Dongandqianlihuang d940607629 [Core] Support min_tokens with speculative decoding (#32642)
Signed-off-by: qianlihuang <yiliu.dong@qq.com>
Co-authored-by: qianlihuang <yiliu.dong@qq.com>
2026-02-26 12:31:28 -05:00
Kunshang Ji 8ad54a991b [Platform] Add current_platform.num_compute_units interface (#35042)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
2026-02-24 22:22:49 -08:00
Kunshang Ji 92510edc32 remove cuda check in top_k_top_p_triton kernel (#35011)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
2026-02-24 22:22:31 -08:00
Xiao Li 30132cd144 Fix apply_top_k_top_p_triton called by non-cuda logits Tensor (#35030)
Signed-off-by: Xiao Li <ilx@meta.com>
2026-02-21 21:11:54 -08:00
Xin Yang 7a5adad480 [Kernel] Optimize sample_recovered_tokens_kernel (#34974)
Signed-off-by: Xin Yang <xyangx@amazon.com>
2026-02-20 19:59:06 -08:00
c656ba3b4d [Kernel] Triton-based Top-k and Top-p sampler kernels (#33538)
Signed-off-by: js_park <cakeng@naver.com>
Signed-off-by: Jongseok Park <37990712+cakeng@users.noreply.github.com>
Signed-off-by: Sunga Kim <sunga.kim@berkeley.edu>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Sunga Kim <sunga.kim@berkeley.edu>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
2026-02-17 23:14:30 +00:00
Zhuohan Li d707678dfb Fix num_logprobs parameter description in sampler.py (#34451)
Signed-off-by: Zhuohan Li <zhuohan123@gmail.com>
2026-02-12 18:18:03 -08:00
caozuoba 8980001c93 [perf] v1/spec_decode: skip softmax for all-greedy rejection sampling (#32852)
Signed-off-by: hdj <1293066020@qq.com>
2026-01-31 09:51:26 +00:00
杨朱 · KikiandClaude Opus 4.5 1a7894dbdf [Misc] Replace Optional[X] with X | None syntax (#33332)
Signed-off-by: carlory <baofa.fan@daocloud.io>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-30 01:56:59 -08:00
Wentao Ye f744810184 [Refactor] Remove unused tpu files (#32610)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2026-01-22 15:35:18 -05:00
Pleaplusone 77c16df31d [ROCm][Bugfix] Disable hip sampler to fix deepseek's accuracy issue on ROCm (#32413)
Signed-off-by: ganyi <ygan@amd.com>
2026-01-15 16:35:47 +00:00
zhrrr 97ba96fbe9 [perf][async] support non cpu sync get logprob tensors for spec (#31336)
Signed-off-by: izhuhaoran <izhuhaoran@qq.com>
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
2026-01-09 21:24:51 +00:00
Nick Hill 10ef65eded [BugFix] Fix bad words with speculative decoding (#31908)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
2026-01-07 15:46:42 -05:00
Nick Hill 2ac85a4544 [BugFix] Fix logprobs with spec decode and modified logits (#30846)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-12-18 19:58:28 -08:00
realliujiaxu d2c919dcc2 [bugfix] fix bug when top_logprobs=0 with spec decoding (#30059)
Signed-off-by: realliujiaxu <realliujiaxu@163.com>
2025-12-12 09:03:35 -08:00
jthomson04 1528e079e2 [Perf] Avoid pageable HtoD transfer in MinTokensLogitsProcessor (#29826)
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
2025-12-02 21:25:52 +00:00
Cyrus Leung 9e6bcda3ac [mypy] Enable type checking for more directories (#29674)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-11-28 08:39:27 -08:00
Harry MellorandCyrus Leung 9eec282cb5 Guard FlashInfer sampler using the same check as FlashInfer attention backend (#29415)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2025-11-28 08:34:48 -08:00
Didier Durand 66d3d5422c [Doc]: fixing typos in diverse files (#29492)
Signed-off-by: Didier Durand <durand.didier@gmail.com>
2025-11-27 07:15:50 -08:00
Nick Hill 4e57c6587f [Core] Support logprobs with spec decode + async scheduling (#29223)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-11-25 12:55:24 -08:00
Nick Hill d44a63c6d6 [BugFix] Fix returned logprobs with spec decode + prefill chunking (#29216)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-11-22 22:41:25 +08:00
Jialin Ouyang 30b9c67743 Revert "[Redo] #26368 (#28771)" (#29121)
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
2025-11-20 21:27:45 -08:00
Xiao Li ed6ae1e36a [AITER] [ROCm] Fix crash when loading llama4 model with old aiter version installed, fallback to forward_native implementation (#29124)
Signed-off-by: Xiao Li <ilx@meta.com>
2025-11-20 17:54:35 -08:00
vllmellm 0af3d4f0df [FEAT] [AITER] [ROCm] integrate aiter sampling ops (#26084)
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
2025-11-18 17:28:34 +00:00
d8874c61a5 [Core] Async Scheduling X Spec Decoding Compatibility (#24799)
Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
2025-11-17 12:16:20 -08:00
Cyrus LeungandJialin Ouyang 98b4d389ed [Redo] #26368 (#28771)
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
2025-11-14 22:47:41 -08:00
Nick Hill ac86bff8cb Revert "[Core] Performance: Use list[np.ndarray] instead of list[list… (#28773) 2025-11-14 20:24:00 -08:00
Jialin Ouyang 186352b270 [Core] Performance: Use list[np.ndarray] instead of list[list[int]] for output tokens for GC optimization (#26368)
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
2025-11-14 16:04:04 -08:00
Isotr0py 3f770f4427 [Performance] Cache loaded custom logitsprocs to avoid overheads (#28462)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-11-11 16:49:29 -08:00
Zhang Xiangze 7bdb42b2f2 [CPU]Avoid repeated random sample compile (#28260)
Signed-off-by: Zhang Xiangze <Xiangze.Zhang@arm.com>
2025-11-07 11:03:57 +00:00
Isotr0py 3f5a4b6473 [Bugfix] Validate custom logits processor xargs for online serving (#27560)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-11-05 16:53:33 +00:00
Nick Hill c2ed069b32 [BugFix] Fix mixed penalties batch with async scheduling (#27910)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-11-01 10:51:24 -07:00
Wentao Ye 52efc34ebf [Log] Optimize Startup Log (#26740)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-24 19:27:04 -04:00
Jonathan Chen ca76486a16 [Chore] Separate out vllm.utils.platform_utils.py (#27374)
Signed-off-by: Jonathan <chenleejonathan@gmail.com>
2025-10-23 19:08:06 +00:00
Giancarlo DelfinandNick Hill 6644796bf4 [V1][spec decode] return logprobs for spec decoding (#26060)
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-10-22 22:59:59 -07:00
Isotr0py 6ac5e06f7c [Chore] Clean up pytorch helper functions in vllm.utils (#26908)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: isotr0py <2037008807@qq.com>
2025-10-18 09:48:22 -07:00
Pradyun92andPradyun Ramadorai acedc74b1a [V1][Spec Decode] Fix greedy temperature detection after sampler refactor (#27077)
Signed-off-by: Pradyun Ramadorai <pradyunr@amazon.com>
Co-authored-by: Pradyun Ramadorai <pradyunr@amazon.com>
2025-10-17 13:27:47 -07:00
Jee Jee Li fec2b341ad [Kernel] Lazy import FlashInfer (#26977) 2025-10-17 04:48:18 +00:00
Akash kaothalkarandAkash Kaothalkar f7d318de2b [Hardware][CPU][PowerPC]Disable torch.compile() in toptopk sampling (#26987)
Signed-off-by: Akash Kaothalkar <akash.kaothalkar@ibm.com>
Co-authored-by: Akash Kaothalkar <akash.kaothalkar@ibm.com>
2025-10-15 22:36:59 -07:00
Michael Goin e66d787bce Disable FlashInfer sampler by default (#26859)
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-10-15 02:35:18 +00:00
ihb2032 4a61950f4d [Hardware][CPU] Disable torch.compile for RISC-V to prevent APIError (#26693)
Signed-off-by: lyd1992 <liuyudong@iscas.ac.cn>
Signed-off-by: ihb2032 <1355790728@qq.com>
Signed-off-by: lyd1992 <liuyudong@iscas.ac.cn
2025-10-13 07:56:01 -07:00
Harry Mellor 8fcaaf6a16 Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-10-12 09:51:31 -07:00
Nick Hill ddcbc2f334 [Misc] Misc code simplifications (#26450)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-10-09 02:10:06 -07:00
Harry Mellor e09d1753ec Remove Python 3.9 support ahead of PyTorch 2.9 in v0.11.1 (#26416)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-10-08 10:40:42 -07:00
Harry Mellor 2f99f2f506 Tidy vllm/config/__init__.py to only add classes and functions (#26405)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-10-08 07:10:00 -07:00
6ebaf43ee4 [V1] Logit processors for rejection sampler (#19482)
Signed-off-by: southfreebird <yvorott@gmail.com>
Signed-off-by: Sergei Skvortsov <sergeyskv@nebius.com>
Signed-off-by: Sergei Skvortsov <yvorott@gmail.com>
Co-authored-by: Sergei Skvortsov <sergeyskv@nebius.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-10-07 13:02:49 -07:00
Harry Mellor b893d661b1 Fix per file ruff ignores related to simplification (#26259)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-10-05 20:31:53 +00:00
Harry Mellor d6953beb91 Convert formatting to use ruff instead of yapf + isort (#26247)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-10-05 07:06:22 -07:00
Corey Lowman 0879736aab [Perf] Remove hardcoded num_warps=1 (#26183)
Signed-off-by: Corey Lowman <clowman1993@gmail.com>
2025-10-03 20:38:50 +00:00
Ekagra RanjanandNick Hill e71b8e210d [Spec Decode] Add Batch Parallel Ngram. Upto 8x lower overhead. (#24986)
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-09-25 15:22:03 -07:00