|
|
ad0297d113
|
[Misc] Support passing multiple request ids at once to AsyncLLM.abort() (#22944)
Signed-off-by: Nick Hill <nhill@redhat.com>
|
2025-08-15 17:00:36 -07:00 |
|
|
|
3e2f7985a2
|
Support multiple attention groups for KV sharing (#22672)
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
|
2025-08-15 16:54:10 -07:00 |
|
|
|
c280066f9d
|
[v1] Move block_hashes from KVCacheManager to Request.block_hashes (#19728)
Signed-off-by: Or Ozeri <oro@il.ibm.com>
|
2025-08-15 16:52:52 -07:00 |
|
|
|
b9dc9d2607
|
[BugFix] Handle case where async utility call is cancelled (#22996)
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Yinghai Lu <yinghai@thinkingmachines.ai>
|
2025-08-15 17:38:42 -06:00 |
|
|
|
74f441f4b5
|
[Core] Allow full cudagraph with separate attention routines and orthogonal to compilation, add support for FA2 and FlashInfer (#20059)
Signed-off-by: fhl <2410591650@qq.com>
Signed-off-by: fhl2000 <63384265+fhl2000@users.noreply.github.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
|
2025-08-15 10:01:39 -04:00 |
|
|
|
75531a6c13
|
[V1] [Hybrid] Support using float32 for state in Hybrid Models (Mamba2, Mamba1, Minimax) (#22928)
Signed-off-by: Daniel Afrimi <danielafrimi8@gmail.com>
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Daniel Afrimi <danielafrimi8@gmail.com>
Co-authored-by: Burkhard Ringlein <ngl@zurich.ibm.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
|
2025-08-15 12:57:06 +00:00 |
|
|
|
3d232dbd19
|
[Mamba] - refactor: Renamed mamba_attn to mamba2_attn (#22818)
Signed-off-by: asafg <asafg@ai21.com>
Co-authored-by: asafg <asafg@ai21.com>
|
2025-08-15 06:38:05 +00:00 |
|
|
|
ae05a6d83d
|
[BugFix] Fix port lookup in internal DP LB tests (#22252)
Signed-off-by: Nick Hill <nhill@redhat.com>
|
2025-08-15 11:17:11 +08:00 |
|
|
|
ebcce2cd36
|
[Core] Return final response for aborted requests from AsyncLLM.generate (#22283)
Signed-off-by: Nick Hill <nhill@redhat.com>
|
2025-08-14 14:49:02 -07:00 |
|
|
|
b8ff05361a
|
[CI] Temporarily disable flaky test (#22930)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2025-08-14 19:59:16 +00:00 |
|
|
|
31a500c86f
|
[Core] [N-gram SD Optimization][1/n] Propose tokens with a single KMP (#22437)
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
|
2025-08-13 14:44:06 -07:00 |
|
|
|
b4b78d6317
|
[CI/Build] Fix param mismatch in test_eagle_correctness (#22847)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-08-13 10:55:25 -07:00 |
|
|
|
12817a8ac7
|
[CI] Fix tests/v1/e2e/test_kv_sharing_fast_prefill.py import on test (#22815)
Signed-off-by: NickLucche <nlucches@redhat.com>
|
2025-08-13 10:35:50 -07:00 |
|
|
|
19b927e52d
|
[Core] Use individual MM items in P0/P1 cache and model runner (#22570)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-08-13 07:18:07 -07:00 |
|
|
|
6b794c756c
|
[Nixl][CI] Fix tests (#22806)
Signed-off-by: NickLucche <nlucches@redhat.com>
|
2025-08-13 06:03:53 -07:00 |
|
|
|
d94e3026de
|
[V1] Add tree drafting tests for eagle spec decoding (#22705)
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
|
2025-08-13 04:11:28 -07:00 |
|
|
|
71683ca6f6
|
[V0 Deprecation] Remove multi-step scheduling (#22138)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
|
2025-08-12 20:18:39 -07:00 |
|
|
|
422f22e012
|
[CI][Nixl] Check kv cache layout during handshake (#22745)
Signed-off-by: NickLucche <nlucches@redhat.com>
|
2025-08-12 12:53:52 -07:00 |
|
|
|
3d9d40efde
|
[Bugfix][CI] Fix test_remote_decode_lifecycle.py::test_short_prompt_lifecycle (#22727)
Signed-off-by: NickLucche <nlucches@redhat.com>
|
2025-08-12 07:30:17 -07:00 |
|
|
|
bc8372efc3
|
[Bugfix] Fix erroneous randomly generated cases in bad word testing (#22170)
Signed-off-by: phantomlei <phantomlei3@gmail.com>
|
2025-08-12 02:03:22 -07:00 |
|
|
|
93d0652433
|
[CI] Increase timeout for test_completion_with_image_embeds (#22670)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2025-08-11 20:31:36 -07:00 |
|
|
|
65abe111a3
|
[CI] Skip Tree Attn Test in test_max_len.py to unblock CI (#22664)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2025-08-11 10:36:05 -07:00 |
|
|
|
807d21b80d
|
[BugFix] [Spec Decode] Remove LlamaForCausalLMEagle3 to fix CI (#22611)
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
|
2025-08-11 10:31:36 -07:00 |
|
|
|
16fb668b61
|
fix: NIXL connector transfers partial block to pass full multi-modal context (#21074)
Signed-off-by: GuanLuo <gluo@nvidia.com>
|
2025-08-11 09:40:55 -07:00 |
|
|
|
5898b135ab
|
[BugFix] Fix KVConnectorOutput TPU breakage (#22598)
Signed-off-by: Nick Hill <nhill@redhat.com>
|
2025-08-10 19:33:48 -07:00 |
|
|
|
2a84fb422f
|
[TPU] kv cache update kernel doesn't need to be padded slices to multiple of num_slices_per_block (#22394)
Signed-off-by: Chengji Yao <chengjiyao@gmail.com>
Co-authored-by: Chengji Yao <chengjiyao@gmail.com>
|
2025-08-09 20:49:04 -07:00 |
|
|
|
3d7363e61c
|
[Config] add "qwen" as a native eagle3 target supported model (#22333)
Signed-off-by: lechen <lecself@163.com>
Signed-off-by: LeChen <lecself@163.com>
|
2025-08-09 20:21:05 -07:00 |
|
|
|
9a0c5ded5a
|
[TPU] Add support for online w8a8 quantization (#22425)
Signed-off-by: Kyuyeun Kim <kyuyeunk@google.com>
|
2025-08-08 23:12:54 -07:00 |
|
|
|
17eaaef595
|
[Bugfix] Fix RuntimeError: Index put requires the source and destination dtypes match (#22065)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
|
2025-08-07 19:20:21 -07:00 |
|
|
|
1ee5ead5f8
|
[ROCm] [V1] [SpecDec] Enable Speculative Decoding on ROCm V1 Engine (#21496)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2025-08-07 19:13:17 -07:00 |
|
|
|
7e3a8dc906
|
Remove from_dict from SpeculativeConfig (#22451)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-08-07 10:13:04 -07:00 |
|
|
|
4815b00f54
|
[gpt-oss] Generate ResponseOutputItem from Harmony Message (#22410)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
|
2025-08-07 08:33:25 -07:00 |
|
|
|
a00d8b236f
|
Use float32 for test_completion.py (#22385)
Signed-off-by: Michael Goin <mgoin64@gmail.com>
|
2025-08-07 11:07:47 +08:00 |
|
|
|
1dc8a70b6d
|
[Attention] Support multiple attention metadata builders per kv_cache_spec + proper local attention no hybrid kv cache fix (#21588)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2025-08-06 18:40:52 -07:00 |
|
|
|
46a13949d5
|
[v1] - Mamba1 Attention Metadata (#21249)
Signed-off-by: asafg <asafg@ai21.com>
Co-authored-by: asafg <asafg@ai21.com>
|
2025-08-06 17:03:42 -07:00 |
|
|
|
469b3ffaaa
|
[V1] port xformers backend to v1 (#21342)
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
|
2025-08-05 10:04:46 -07:00 |
|
|
|
0c275ad5ad
|
[V0 Deprecation][TPU] Remove V1 flag check from tests (#22248)
Signed-off-by: NickLucche <nlucches@redhat.com>
|
2025-08-05 06:53:23 -07:00 |
|
|
|
5ea71ff46f
|
[V1] reduce block size for tree attention correctness test to fix 'ou… (#22207)
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
|
2025-08-04 19:11:06 -07:00 |
|
|
|
7175817637
|
Revert "[Bugfix] V1 Fix the cursor leakage issue during request scheduling." (#22223)
|
2025-08-04 18:37:06 -07:00 |
|
|
|
2dffac464c
|
[Bugfix] V1 Fix the cursor leakage issue during request scheduling. (#21173)
Signed-off-by: CLFutureX <775523362@qq.com>
|
2025-08-04 18:34:10 -07:00 |
|
|
|
54de71d0df
|
[Sampler] Support returning all logprobs or logits (#21792)
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
|
2025-08-04 03:04:12 -07:00 |
|
|
|
8ecb3e9e93
|
[CI Bugfix] Fix wNa16 kernel not found for test_shared_storage_connector_hashes (#22163)
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
|
2025-08-03 22:19:04 -07:00 |
|
|
|
aa7012eb6d
|
Add tree attention backend for v1 (part 1) (#20401)
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
|
2025-08-03 22:13:26 -07:00 |
|
|
|
0d7db16a92
|
[PD] add test for chat completions endpoint (#21925)
Signed-off-by: Abirdcfly <fp544037857@gmail.com>
|
2025-08-03 19:57:03 -07:00 |
|
|
|
6d98843b31
|
[Responses API] Disable response store by default (#22137)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-08-03 04:04:21 -07:00 |
|
|
|
aefeea0fde
|
[V1] [P/D] Refactor KV Connector Path (#21980)
Signed-off-by: David Ben-David <davidb@pliops.com>
Co-authored-by: David Ben-David <davidb@pliops.com>
|
2025-08-03 04:03:40 -07:00 |
|
|
|
067c34a155
|
docs: remove deprecated disable-log-requests flag (#22113)
Signed-off-by: Roger Wang <hey@rogerw.me>
|
2025-08-02 00:19:48 -07:00 |
|
|
|
8564dc9448
|
Fix test_kv_sharing_fast_prefill flakiness (#22038)
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
|
2025-08-01 23:55:34 -07:00 |
|
|
|
0edaf752d7
|
[Attention][DBO] Add support for "splitting" the CommonAttentionMetadata (#21153)
Signed-off-by: Sage Moore <sage@neuralmagic.com>
|
2025-08-01 19:47:53 -07:00 |
|
|
|
b879ecd6e2
|
[Bugfix] fix when skip tokenizer init (#21922)
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
|
2025-08-01 10:09:36 -07:00 |
|
