biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
5,615 Commits 2 Branches 140 Tags
b6be6f8d1e49d4aa884603e8675dc216be1cbd79
Commit Graph

186 Commits

Author SHA1 Message Date
wwl2755
463bbb1835 [Bugfix][V1] Fix bug from putting llm_engine.model_executor in a background process (#15367) 
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
 2025-04-03 07:32:10 +00:00
Nicolò Lucchesi
bd7599d34a [V1][TPU] Do not compile sampling more than needed (#15883) 
Signed-off-by: NickLucche <nlucches@redhat.com>
 2025-04-03 01:36:01 +00:00
Chengji Yao
01b6113659 [TPU] optimize the all-reduce performance (#15903) 
Signed-off-by: Chengji Yao <chengjiyao@google.com>
 2025-04-03 00:25:14 +00:00
Eric Tang
ddb94c2605 [core] Add tags parameter to wake_up() (#15500) 
Signed-off-by: Eric <erictang000@gmail.com>
 2025-04-02 01:59:27 -07:00
Woosuk Kwon
e75a6301bd [V1][Spec Decode] Implement Eagle Proposer [1/N] (#15729) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-04-01 12:33:16 -07:00
Chen Zhang
3a5f0afcd2 [V1] Implement sliding window attention in kv_cache_manager (#14097) 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
 2025-04-01 00:33:17 -07:00
Alexander Matveev
9a2160fa55 [V1] TPU CI - Add basic perf regression test (#15414) 
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
 2025-03-31 13:25:20 -04:00
yihong
2de4118243 fix: change GB to GiB in logging close #14979 (#15807) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2025-03-31 10:00:50 -07:00
Cyrus Leung
09e974d483 [Bugfix] Check dimensions of multimodal embeddings in V1 (#15816) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-03-31 09:01:35 -07:00
youkaichao
555aa21905 [V1] Fully Transparent Implementation of CPU Offloading (#15354) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-03-31 20:22:34 +08:00
Chengyang LIU
18ed3132d2 [Misc] update the comments (#15780) 
Signed-off-by: chengyang liu <lcy4869@gmail.com>
Co-authored-by: chengyang liu <lcy4869@gmail.com>
 2025-03-30 19:39:56 -07:00
Cyrus Leung
803d5c35f3 [V1] Override mm_counts for dummy data creation (#15703) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-03-30 03:20:42 -07:00
Woosuk Kwon
2bc4be4e32 [V1][Minor] Simplify rejection sampler's parse_output (#15741) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-03-29 09:25:17 -07:00
yarongmu-google
7c1f760024 [Kernel][TPU][ragged-paged-attn] vLLM code change for PR#8896 (#15659) 
Signed-off-by: Yarong Mu <ymu@google.com>
 2025-03-28 21:13:15 -07:00
Nicolò Lucchesi
da461f3cbf [TPU][V1][Bugfix] Fix w8a8 recompiilation with GSM8K (#15714) 
Signed-off-by: NickLucche <nlucches@redhat.com>
 2025-03-28 21:13:06 -07:00
Alexander Matveev
c3f687ac22 [V1] TPU - Fix the chunked prompt bug (#15713) 
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
 2025-03-28 20:19:04 +00:00
Robert Shaw
038bededba [TPU] [Perf] Improve Memory Usage Estimation (#15671) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
 2025-03-28 17:37:52 +00:00
Cyrus Leung
c6bc0034d0 [Misc] Remove unused utils and clean up imports (#15708) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-03-28 09:41:16 -07:00
Cyrus Leung
355f66348c [V1] Remove legacy input registry (#15673) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-03-27 23:34:34 -07:00
Nicolò Lucchesi
4098b72210 [Bugfix][TPU][V1] Fix recompilation (#15553) 
Signed-off-by: NickLucche <nlucches@redhat.com>
 2025-03-27 19:15:06 +00:00
Cyrus Leung
13ac9cab21 [Misc] Avoid direct access of global mm_registry in compute_encoder_budget (#15621) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-03-27 17:52:00 +00:00
Hiroaki Sugiyama
8958217ad5 [Bugfix] Fix use_cascade_attention handling for Alibi-based models on vllm/v1 (#15211) 
Signed-off-by: h-sugi <h.sugi@ieee.org>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-03-27 22:29:29 +08:00
Chengji Yao
619d3de8bd [TPU] [V1] fix cases when max_num_reqs is set smaller than MIN_NUM_SEQS (#15583) 
Signed-off-by: Chengji Yao <chengjiyao@google.com>
 2025-03-26 22:46:26 -07:00
Cody Yu
54aa619459 [V1] Refactor num_computed_tokens logic (#15307) 
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-03-27 04:54:36 +00:00
Chengji Yao
e74ff409e0 [TPU] support disabling xla compilation cache (#15567) 
Signed-off-by: Chengji Yao <chengjiyao@google.com>
 2025-03-27 00:09:28 +00:00
Alexander Matveev
b2e85e26f4 [V1] TPU - Revert to exponential padding by default (#15565) 
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
 2025-03-26 21:35:05 +00:00
Chenyaaang
ac3cd6e83c [core] add bucket padding to tpu_model_runner (#14995) 
Signed-off-by: Chenyaaang <llccyy1212@gmail.com>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Co-authored-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
 2025-03-25 17:27:22 -04:00
Nicolò Lucchesi
a0dd7dcd49 [TPU][V1] Fix Sampler recompilation (#15309) 
Signed-off-by: NickLucche <nlucches@redhat.com>
 2025-03-25 16:43:54 -04:00
Siyuan Liu
4157f563b4 [Hardware][TPU][Bugfix] Fix v1 mp profiler (#15409) 
Signed-off-by: Siyuan Liu <lsiyuan@google.com>
 2025-03-25 01:43:00 -07:00
Woosuk Kwon
25f560a62c [V1][Spec Decode] Update target_logits in place for rejection sampling (#15427)
Some checks failed
Create Release / Create Release (push) Has been cancelled
Details 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-03-24 21:04:41 -07:00
Nick Hill
3aee6573dc [V1] Aggregate chunked prompt logprobs in model runner (#14875) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-03-24 12:27:57 -04:00
Woosuk Kwon
b9bd76ca14 [V1][Spec Decode] Respect prompt_lookup_max (#15348) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-03-23 10:41:44 -07:00
shangmingc
50c9636d87 [V1][Usage] Refactor speculative decoding configuration and tests (#14434) 
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
 2025-03-22 19:28:10 -10:00
Chen Zhang
93a00d7dde [v1] Refactor KVCacheConfig (#14079) 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
 2025-03-21 04:56:27 -07:00
Siyuan Liu
b15fd2be2a [Hardware][TPU] Add check for no additional graph compilation during runtime (#14710) 
Signed-off-by: Siyuan Liu <lsiyuan@google.com>
 2025-03-21 03:05:28 +00:00
Woosuk Kwon
0c6f5023c3 [V1] Scheduler Refactoring [1/N] - Add Scheduler Interface (#15250) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
 2025-03-20 17:50:43 -07:00
Woosuk Kwon
2b22290ce0 [V1] Add flag to disable cascade attention (#15243) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-03-20 15:24:16 -07:00
Mickaël Seznec
a597a57595 [Attention] Flash Attention 3 - fp8 (#14570) 
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
 2025-03-20 01:14:20 -04:00
Nicolò Lucchesi
d8c6d7d6b5 [V1][TPU] Support V1 Sampler for ragged attention (#14227) 
Signed-off-by: NickLucche <nlucches@redhat.com>
 2025-03-19 21:00:39 -07:00
Woosuk Kwon
99abb8b650 [V1][Spec Decode] Optimize Rejection Sampler with Triton Kernels (#14930) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-03-18 14:31:54 -07:00
Nicolò Lucchesi
af35d3a3cc [TPU][V1][Bugfix] Fix chunked prefill with padding (#15037) 
Signed-off-by: NickLucche <nlucches@redhat.com>
 2025-03-18 07:34:45 -07:00
Varun Sundar Rabindranath
400d483e87 [Kernels] LoRA - Retire SGMV and BGMV Kernels (#14685) 
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
 2025-03-18 09:47:53 +00:00
iefgnoix
b4ad56c1bd [V1][TPU] Apply the ragged paged attention kernel fix and remove the padding. (#14846) 
Signed-off-by: Xiongfei Wei <isaacwxf23@gmail.com>
 2025-03-17 01:48:28 -07:00
Cyrus Leung
b539222d4e [V1] Remove input cache client (#14864) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
 2025-03-16 23:42:06 -07:00
Lily Liu
8d6cf89526 [V1] [Spec Decode] Support random sampling for spec decode (#13933)
Some checks failed
Create Release / Create Release (push) Has been cancelled
Details 
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-03-16 22:00:20 -07:00
Woosuk Kwon
faa0275730 [V1] Optimize the overhead of rewinding (#14905) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-03-16 20:19:30 -07:00
Woosuk Kwon
31060b2757 [V1][BugFix] Detect interleaved sliding window attention (#14896) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-03-16 14:53:53 -07:00
Nick Hill
fc1f67715d [BugFix][V1] Fix overhead related to bad_words sampling when not in use (#14894) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-03-16 14:53:34 -07:00
Roger Wang
ad19c8a003 [V1] Move OOM check into sampler run (#14728) 
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
 2025-03-13 20:40:23 -07:00
Benjamin Chislett
5c538c37b2 [V1][Bugfix][Spec Decode] Fix incorrect outputs in V1 speculative decoding due to batch indexing (#14645) 
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
 2025-03-11 22:12:41 -07:00