Skip to content

[doc][https://nvbugs/6675989] Explicitly label addition of flag use_paged_context_fmha as a code snippet #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
thorjohnsen wants to merge 1,716 commits into from
Closed

[doc][https://nvbugs/6675989] Explicitly label addition of flag use_paged_context_fmha as a code snippet #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1716 commits
Select commit Hold shift + click to select a range
6d9fbea
[None][infra] Fix CBTS skip-rate calculation method (#16467)
crazydemo Aug 26, 2026
9a200a5
[https://nvbugs/6647349][fix] Replace FuzzyWuzzy with RapidFuzz (#18201)
lfr-0531 Aug 26, 2026
1b19a81
[None][fix] Stabilize Gemma4 FA2 CUDA Graph decode on Hopper (#18002)
lfr-0531 Aug 26, 2026
3e2749f
[https://nvbugs/6596590][fix] Densify warmup mesh for sparse fmha ker…
pengbowang-nv Aug 26, 2026
15f92dc
[TRTLLM-15748][chore] Remove dead code and de-reflect lazy attributes…
lori-ren Aug 26, 2026
f4449ae
[None][infra] Waive 1 failed cases for main in pre-merge 56702 (#18245)
trtllm-agent Aug 26, 2026
38c824b
[None][feat] Add nvfp4 situ moe cubins (#17940)
rosong11 Aug 26, 2026
0cb928b
[https://nvbugs/6647310][chore] Unwaive TestLagunaXS::test_nvfp4 (#18…
sunnyqgg Aug 26, 2026
7e19254
[https://nvbugs/6669902][test] Waive minimax_m3 tests broken by the b…
JunyiXu-nv Aug 26, 2026
1c3d13b
[None][chore] Add Top-K code owners (#18246)
yuxianq Aug 26, 2026
cd508a1
[None][ci] disable autodeploy test stages (#18107)
QiJune Aug 26, 2026
8bde010
[https://nvbugs/6422432][fix] Unwaive testcase (#17947)
YihuiLu512 Aug 26, 2026
ed94d4c
[TRTLLM-15293][perf] Add self-sampling (GVR V2) top-K decode kernels …
longcheng-nv Aug 26, 2026
16260e5
[https://nvbugs/6525010][fix] Isolate torch compile test sessions (#1…
liji-nv Aug 26, 2026
4288390
[None][perf] Compute response GPU timings once per batch (#18053)
liji-nv Aug 26, 2026
ca939b7
[https://nvbugs/6579626][perf] Fallback small BF16 context batches (#…
yihwang-nv Aug 26, 2026
590c2fd
[None][fix] Multimodal Mixin Guided Decoder Delegation (#18162)
aswinvisva Aug 26, 2026
45f2b13
[https://nvbugs/6327718][fix] Drain EPD thread pool before proxy shut…
aswinvisva Aug 26, 2026
574bd60
[None][infra] Waive 1 failed cases for main in pre-merge 56793 (#18258)
trtllm-agent Aug 26, 2026
5ae89d6
[None][fix] Simplify idle disagg KV transfer progress check (#17324)
Tabrizian Aug 26, 2026
fa77839
[None][ci] waive pre-existing test failures on main (#18191)
brnguyen2 Aug 26, 2026
0c68b4f
[https://nvbugs/6652876][fix] Add correct autotuner constraint for sm…
DomBrown Aug 26, 2026
ddd6206
[None][infra] Set --platform when retagging CI image (#18208)
yuanjingx87 Aug 26, 2026
599448d
[None][fix] Drop the unbound is_idle guard left in the idle disagg CT…
pranav-nvidia Aug 26, 2026
c2f5f31
[TRTLLMINF-339][infra] Enable BOLT profile-gen producer (job + cadenc…
mlefeb01 Aug 26, 2026
767af6f
[None][perf] Cut per-iteration executor bookkeeping in the hang detec…
pranav-nvidia Aug 26, 2026
9fc603b
[TRTLLM-15030][fix] CuteDSL MLA decode follow-ups: bucket AutoTuner f…
brnguyen2 Aug 27, 2026
36138a2
[https://nvbugs/6644226][fix] Reduce DeepSeek V4 EPLB loading memory …
lfr-0531 Aug 27, 2026
6eb66fa
[None][infra] Waive 1 failed cases for main in pre-merge 56772 (#18281)
trtllm-agent Aug 27, 2026
c170995
[None][test] Consolidate ssm dis-agg E2E Tests (#17680)
bo-nv Aug 27, 2026
d550906
[TRTLLM-9905][infra] Upload results periodically (#14138)
yiqingy0 Aug 27, 2026
6a44fe7
[TRTLLMINF-187][fix] Drain S3 test logs from rank zero (#18240)
niukuo Aug 27, 2026
34847b8
[None][infra] CBTS coverage arch combine v2 (#18058)
crazydemo Aug 27, 2026
1412603
[None][doc] Point the dis-agg docs at transceiver v2 (#18248)
Shixiaowei02 Aug 27, 2026
8e16551
[TRTLLMINF-263][infra] pass nSpect release entitlement (#18217)
niukuo Aug 27, 2026
f946837
[None][infra] Check in most recent lock file from nightly pipeline
tensorrt-cicd Aug 27, 2026
e8fd8c0
[TRTLLM-15498][perf] eliminate KDA recurrent-state and metadata copie…
jiaganc Aug 27, 2026
64ca8ad
[TRTLLM-15108][test] clean obsolete qwen tests (#17827)
xinhe-nv Aug 27, 2026
6589a4e
[None][infra] Upload build info during pipeline setup (#18237)
crazydemo Aug 27, 2026
3035d47
[None][infra] Upgrade NIXL to v1.4.0 and UCX to v1.22.x (#17891)
zackyoray Aug 27, 2026
aaa62b2
[None][test] Remove unused performance test utilities and clean up te…
yufeiwu-nv Aug 27, 2026
2e70be3
[None][feat] Add locality domain runtime and bindings for Rubin (#17662)
zhangcl Aug 27, 2026
9769ff1
[TRTLLM-12758][feat] honor named function in tool_choice for non-harm…
JunyiXu-nv Aug 27, 2026
0a41020
[https://nvbugs/6581067][fix] Request the unbiased GEMM in fp32 and a…
trtllm-agent Aug 27, 2026
7cae26e
[None][infra] Waive 1 failed cases for main in pre-merge 56942 (#18303)
trtllm-agent Aug 27, 2026
8e7a8ff
[https://nvbugs/6663062][fix] remove Mistral moe tests (#18288)
xinhe-nv Aug 27, 2026
c110d1d
[None][feat] laguna: config-driven sqrt-softplus router scoring (#17918)
Aug 27, 2026
d094b51
[https://nvbugs/6660905][fix] Gate TritonFusedMoE on the SwiGLU famil…
xxi-nv Aug 27, 2026
52b4279
[None][chore] Make disagg test paths sole-owned by disagg-devs (#18235)
Shixiaowei02 Aug 27, 2026
785c948
[https://nvbugs/6645731][fix] align logprobs with token_ids when stop…
Wanli-Jiang Aug 27, 2026
b460237
[TRTLLM-15498][perf] fuse KDA beta preprocessing and isolate FLA fall…
jiaganc Aug 27, 2026
d6ed25c
[TRTLLMINF-345][doc] clarify nightly release installation (#18282)
chzblych Aug 27, 2026
88f7969
[None][feat] k3 weight pipeline opt (#17741)
WeiHaocheng Aug 27, 2026
43ba505
[https://nvbugs/6337224][test] Unwaive test_config_database_tests_syn…
hyukn Aug 27, 2026
528a530
[TRTLLM-15316][feat] Rubin sm107 trtllm-gen gemms (#18197)
farazkh80 Aug 27, 2026
4679927
[TRTLLM-15894][feat] Responses API: complete the /v1/responses surfac…
JunyiXu-nv Aug 27, 2026
710fd25
[TRTLLM-14874][feat] Refactor advanced-sampling CUDA graph capture (#…
asfiyab-nvidia Aug 27, 2026
682fa40
[None][perf] Histogram top-k for MiniMax-M3 block selector (#18154)
brb-nv Aug 27, 2026
507f2a5
[TRTLLMINF-339][infra] Declare BoltProfileGen's SCM pass-through para…
mlefeb01 Aug 27, 2026
d0d0173
[https://nvbugs/6571410][fix] Move Gemma4 perf test to post-merge (#1…
2ez4bz Aug 27, 2026
85ae713
[None][chore] Update blossom-ci allowlist (#18315)
yuanjingx87 Aug 27, 2026
6bfd454
[https://nvbugs/6572838][fix] Fix LLM-only behavior for Mistral large…
2ez4bz Aug 27, 2026
8d6bf99
[TRTLLM-15036][test] Add Kimi K3 GSM8K/MMMU accuracy tests and regist…
moraxu Aug 27, 2026
68e97d9
[https://nvbugs/6644468][fix] Defer the four runner imports to their …
trtllm-agent Aug 27, 2026
732cd83
[https://nvbugs/6384357][fix] Fail stop distributed warmup errors (#1…
pranav-nvidia Aug 27, 2026
3fde2c5
[https://nvbugs/6681216][infra] Waive DeepSeek V3 Lite NIXL on B200 a…
chienchunhung Aug 27, 2026
d210366
[https://nvbugs/6650463][fix] Let CutlassFusedMoE serve MXFP8 under M…
xxi-nv Aug 27, 2026
4107854
[None][feat] Make the Python KV-cache transceiver the default runtime…
nv-xtf Aug 28, 2026
6c344c3
[None][refactor] Split connector KV save out of _send_kv_async (#18186)
nv-xtf Aug 28, 2026
fef3372
[None][test] Update GB300 MiniMax-M3 waive (#18332)
jieli-matrix Aug 28, 2026
648e717
[None][perf] Fuse relu2 into a single elementwise kernel (#18082)
nv-guomingz Aug 28, 2026
bd03d5f
[None][fix] Keep CuTe-DSL MLA decode for Kimi K3 H=96 speculative-ver…
moraxu Aug 28, 2026
b08deaa
[None][infra] Cache merge request file changes for CBTS (#18309)
crazydemo Aug 28, 2026
c845c18
[None][infra] Check in most recent lock file from nightly pipeline
tensorrt-cicd Aug 28, 2026
96c8d56
[None][feat] Add perf-analyze and perf-optimize workflows to agent-fl…
kaiyux Aug 28, 2026
e8d7672
[https://nvbugs/6581071][fix] Pass the SM explicitly as `is_nvfp4_mar…
trtllm-agent Aug 28, 2026
6f7a13c
[None][perf] SM120 optimizations for Qwen3.6-35B-A3B-NVFP4 (#17976)
amukkara Aug 28, 2026
54478a0
[None][infra] Waive 5 failed cases for main in post-merge 2932 (#18340)
trtllm-agent Aug 28, 2026
ec411dc
[None][feat] Enable CuTe DSL MLA with Helix (#18131)
mingyangHao Aug 28, 2026
ad84866
[TRTLLM-15314][fix] recalculate PEFT cache capacity for adapter dtype…
achartier Aug 28, 2026
e68f581
[TRTLLM-14116][feat] Add DeepSeek-V4 Hopper support (#16940)
lfr-0531 Aug 28, 2026
4fa30d2
[None][infra] Waive failed cases for main in pre-merge 56812 (#18283)
trtllm-agent Aug 28, 2026
2938ada
[None][feat] Cosmos3 action generation (#17325)
ishovkun Aug 28, 2026
bd675a5
[None][infra] Retry SLURM agent online timeouts (#17586)
Mgluhovskoi Aug 28, 2026
263921f
[None][test] Don't force disable_overlap_scheduler for perf-sanity ct…
chenfeiz0326 Aug 28, 2026
891b483
[None][feat] Consolidate the DSpark draft paths and support standalon…
dc3671 Aug 28, 2026
40b9cbc
[https://nvbugs/6670227][fix] Drop redundant min_tokens from DSv4-Pro…
zhaoyangwang-nvidia Aug 28, 2026
7b4f740
[https://nvbugs/6337228][fix] In tests/unittest/tools/test_layer_wise…
tensorrt-cicd Aug 28, 2026
390f92d
[None][infra] Waive 7 failed cases for main in post-merge 2934 (#18361)
trtllm-agent Aug 28, 2026
c7b8ec2
[None][doc] Add human-in-the-loop section to modeling-bringup README …
WeiHaocheng Aug 28, 2026
2dddac6
[TRTLLM-15498][perf] optimize Kimi KDA prefill convolution data flow …
jiaganc Aug 28, 2026
7110513
[None][infra] Declare and pin CI-imported deps to prevent transitive …
brnguyen2 Aug 28, 2026
5767bed
[https://nvbugs/6571418][test] Unwaive DeepSeek-V4-Pro GSM8K accuracy…
lfr-0531 Aug 28, 2026
f077d4a
[TRTLLM-15585][feat] Wire SkipSoftmax sparse attention into the CuTeD…
karljang Aug 28, 2026
a662631
[#17016][feat] Add selectable OpenEngine gRPC server (#17084)
connorcarpenter15 Aug 28, 2026
3c4dc51
[https://nvbugs/6480621][test] Revert to 60-second KV transfer timeou…
chienchunhung Aug 28, 2026
5a97004
[TRTLLMINF-324][infra] Extend infra-scoped fail-fast to the build→con…
brnguyen2 Aug 28, 2026
32655ab
[https://nvbugs/6669206][test] Unwaive test_kimi_k3_gen_dep[1] fixed …
brnguyen2 Aug 28, 2026
15040dd
[None][test] Unwaive test_trtllm_bench_llmapi_launch for nvbugs/65680…
allisonlim-nv Aug 28, 2026
61aa99a
[https://nvbugs/6644644][fix] Replay both verified orphan payloads on…
trtllm-agent Aug 28, 2026
c3fd8ca
[None][chore] Refine runtime CODEOWNERs (#18318)
mikeiovine Aug 28, 2026
61083f4
[TRTLLM-14604][fix] add auth for RL endpoints (#17434)
hchings Aug 28, 2026
11d8ef1
[TRTLLM-14764][feat] trtllm-serve: Kimi K3 API compliance for the Kim…
moraxu Aug 28, 2026
ef3124d
[None][ci] Waive flaky TestGemma3_1BInstruct::test_auto_dtype[False] …
brnguyen2 Aug 28, 2026
57db9f4
[https://nvbugs/6641268][fix] Use fallback FMHA for SM103 context att…
yuxianq Aug 29, 2026
2e5dbe0
[https://nvbugs/6581049][ci] Unwaive test (#18394)
2ez4bz Aug 29, 2026
7b60a56
[None][fix] Fix Gemma4 video token counting (#18274)
2ez4bz Aug 29, 2026
1acd695
[None][infra] Check in most recent lock file from nightly pipeline
tensorrt-cicd Aug 29, 2026
cb511b5
[TRTLLM-15376][test] expand Gemma 4 MTP QA coverage (#18218)
jieli-matrix Aug 29, 2026
c44de1a
[TRTLLM-15316][feat] sm107 gemm + quant (#17485)
farazkh80 Aug 29, 2026
2bc0a99
[TRTLLMINF-336][infra] BOLT profile merge: skip runtime tensorrt impo…
mlefeb01 Aug 29, 2026
77cc145
[TRTLLM-15405][refactor] BREAKING: Remove TRTLLMSampler and sampler_t…
zhaoyangwang-nvidia Aug 29, 2026
c5c985c
[TRTLLM-14843][chore] Establish _torch/moe/ and relocate MoE modules,…
lori-ren Aug 30, 2026
26c1c12
[None][infra] Check in most recent lock file from nightly pipeline
tensorrt-cicd Aug 30, 2026
e53a70c
[https://nvbugs/6640776][fix] Bump CUTLASS DSL to 4.6.2 to unblock FA…
trtllm-agent Aug 30, 2026
ffdffe8
[None][test] Unwaive GB300 MiniMax M3 NVFP4 test (#18400)
jieli-matrix Aug 30, 2026
6c1ce33
[None][chore] Update trtllm-gen FMHA kernels and cubins (#18183)
kris1025 Aug 30, 2026
c0503c2
[None][infra] Waive 1 failed cases for main in post-merge 2938 (#18415)
trtllm-agent Aug 31, 2026
775015b
[None][chore] Apply clang-format to FMHA kernel header (#18417)
chzblych Aug 31, 2026
c77f319
[https://nvbugs/6650388][chore] Unwaive TestDeepSeekV32 nvfp4 chunked…
zhaoyangwang-nvidia Aug 31, 2026
f787e8a
[https://nvbugs/6647405][fix] Do not sleep out the KV transfer poll i…
chuangz0 Aug 31, 2026
8b1f345
[None][test] Waive 6 failed cases for main in QA CI (#18418)
trtllm-agent Aug 31, 2026
ad66327
[None][feat] Support custom masks in TRTLLM attention (#16214)
yuxianq Aug 31, 2026
73ee6b0
[None][test] Waive 2 failed cases for main in QA CI (#18419)
trtllm-agent Aug 31, 2026
9332a81
[#18338][fix] Fix barrier-divergence races in the Blackwell CuTe DSL …
zkyue Aug 31, 2026
36808bd
[None][test] Add MiniMax-M3 disaggregated perf recipes to QA multi-no…
fredricz-20070104 Aug 31, 2026
5b09f87
[https://nvbugs/6384625][fix] Unwaive testcase (#18286)
YihuiLu512 Aug 31, 2026
0d4cf39
[https://nvbugs/6633928][test] Unwaive Gemma3 FP8 accuracy test on H1…
erictsai-nv Aug 31, 2026
acf1dad
[None][infra] Check in most recent lock file from nightly pipeline
tensorrt-cicd Aug 31, 2026
2e041d1
[None][infra] Waive 7 failed cases for main in post-merge 2938 (#18420)
trtllm-agent Aug 31, 2026
ea8f861
[None][test] Waive 3 failed cases for main in QA CI (#18423)
trtllm-agent Aug 31, 2026
3d2b26e
[None][test] key perf-sanity case identity on test case name (#18408)
chenfeiz0326 Aug 31, 2026
66f684b
[TRTLLMINF-339][infra] enable BOLT profile overlay on published conta…
mlefeb01 Aug 31, 2026
f9d11b2
[https://nvbugs/6402009][test] unwaive Qwen3-235B NVFP4 TRTLLM MoE te…
jiahanc Aug 31, 2026
cfd7cf1
[None][feat] KVCacheManagerV2: suspend/resume observability stat + co…
eopXD Aug 31, 2026
db1ce32
[TRTLLM-15883][infra] clarify CBTS fallback diagnostics (#18422)
crazydemo Aug 31, 2026
be3fecb
[None][test] Add AgentX DeepSeek-V4-Pro-DSpark perf-sanity lanes on G…
chenfeiz0326 Aug 31, 2026
e052d14
[None][feat] Prefer POSIX FD handle type for KV cache V2 VMM allocati…
chuangz0 Aug 31, 2026
12f5545
[None][chore] Bump version to 1.3.0rc26 (#18402)
yuanjingx87 Aug 31, 2026
1b191b6
[None][test] Waive 1 failed cases for main in QA CI (#18435)
trtllm-agent Aug 31, 2026
23e8905
[None][test] Waive 11 failed cases for main in QA CI (#18438)
trtllm-agent Aug 31, 2026
879603a
[None][test] Waive 1 failed cases for main in QA CI (#18439)
trtllm-agent Aug 31, 2026
5fa3078
[TRTLLMINF-371][infra] Run pre-commits checks on all files if there a…
yiqingy0 Aug 31, 2026
b6cb3d6
[None][infra] Add GB300 multi-node post-merge stages for Qwen3.8-2.4T…
Wanli-Jiang Aug 31, 2026
1151605
[None][test] Waive 1 failed cases for main in QA CI (#18451)
trtllm-agent Aug 31, 2026
f21fb00
[None][test] Waive 2 failed cases for main in QA CI (#18453)
trtllm-agent Aug 31, 2026
33d1a3c
[TRTLLM-11412][feat] Add offloading support for visual_gen (#14095)
rahul-steiger-nv Aug 31, 2026
03eb1a3
[TRTLLM-12680][feat] add exit code telemetry (#17377)
Mgluhovskoi Aug 31, 2026
20fe04a
[None][infra] Waive 1 failed cases for main in pre-merge 57535 (#18452)
trtllm-agent Aug 31, 2026
4c2ba54
[None][refactor] Harden the KvCacheTransceiver contract and add a con…
nv-xtf Aug 31, 2026
4593e50
[TRTLLM-14575][perf] Batch DSA cross-layer index remap into one kerne…
xwang233 Aug 31, 2026
19356d5
[TRTLLM-14778][perf] Add feature-mode encoder CUDA graphs for fixed-s…
pranav-nvidia Aug 31, 2026
5b32a5f
[https://nvbugs/6698722][test] Waive Gemma3 1B disagg KV-cache-v2 NIX…
brnguyen2 Aug 31, 2026
6f6f069
[TRTLLM-14880][feat] qualify Qwen3 dense for MX (#17142)
chienchunhung Aug 31, 2026
3d466db
[TRTLLM-14705][fix] Kimi K3 B200 enablement: MLA decode dispatch fix,…
moraxu Aug 31, 2026
5d979ef
[None][doc] Remove invalid html_inline entry from myst_enable_extensi…
nv-guomingz Aug 31, 2026
2ca8aae
[https://nvbugs/6633929][fix] Fix XGrammar structural tag doc links a…
nv-guomingz Aug 31, 2026
c28bd30
[https://nvbugs/6676032][doc] Give a runnable lm_eval install command…
nv-guomingz Aug 31, 2026
aada226
[https://nvbugs/6676066][doc] Clone examples/llm-api before running t…
nv-guomingz Aug 31, 2026
05bf7b4
[https://nvbugs/6626445][fix] Narrow Wan2.2 I2V test fixture scope to…
o-stoner Aug 31, 2026
6e6f506
[None][doc] Update GLM-5 docs for GLM-5.3 and disaggregated serving (…
brnguyen2 Aug 31, 2026
99395c5
[https://nvbugs/6384357][test] Unwaive DeepSeek-V3.2 DSA host cache o…
pranav-nvidia Sep 1, 2026
5c5a5d8
[None][infra] Waive 1 failed cases for main in pre-merge 57472 (#18468)
trtllm-agent Sep 1, 2026
b621454
[None][infra] Waive 1 failed cases for main in pre-merge 57672 (#18467)
trtllm-agent Sep 1, 2026
d70260a
[TRTLLM-15800][feat] bench_moe: hybrid MoE TP x EP parallel modes (#1…
guqiqi Sep 1, 2026
d62fc67
[None][perf] optimize DSpark attention (#18061)
mingyangHao Sep 1, 2026
ca0b685
[None][test] Waive 2 failed cases for main in QA CI (#18472)
trtllm-agent Sep 1, 2026
c1d0134
[None][infra] Waive 6 failed cases for main in post-merge 2941 (#18473)
trtllm-agent Sep 1, 2026
69889e1
[None][test] Waive 2 failed cases for main in QA CI (#18475)
trtllm-agent Sep 1, 2026
22e4cbc
[https://nvbugs/6676511][fix] Reject unsupported speculative outputs …
2ez4bz Sep 1, 2026
109f211
[TRTLLM-14575][perf] Use native next_n for DSA paged-MQA on Blackwell…
xwang233 Sep 1, 2026
b6fc74f
[https://nvbugs/6644487][fix] Unwaive one case which might be fixed (…
EmmaQiaoCh Sep 1, 2026
de57b1e
[None][feat] Add perf-analyze and perf-optimize skills to agent-flow …
kaiyux Sep 1, 2026
d717506
[None][infra] Check in most recent lock file from nightly pipeline
tensorrt-cicd Sep 1, 2026
07c5f21
[None][perf] Convolve the Mamba2 prefill on a channel-last projection…
nv-guomingz Sep 1, 2026
75593a2
[TRTLLM-11446][feat] trtllm-eval visual-gen generation evaluation pip…
yibinl-nvidia Sep 1, 2026
b53be97
[None][test] Waive 2 failed cases for main in QA CI (#18481)
trtllm-agent Sep 1, 2026
f3359be
[None][infra] Lower GB300 16-GPU accuracy test timeout to 90 minutes …
Wanli-Jiang Sep 1, 2026
418b970
[None][infra] Waive 1 failed cases for main in pre-merge 57744 (#18494)
trtllm-agent Sep 1, 2026
39d915c
[None][infra] Waive 1 failed cases for main in pre-merge 57684 (#18495)
trtllm-agent Sep 1, 2026
24ab1fa
[https://nvbugs/6649386][chore] Unwaive disaggregated deepseek_r1_v2_…
zhaoyangwang-nvidia Sep 1, 2026
12ec475
[TRTLLM-15820][feat] Enable Nemotron Super 3.5 VL video input (#18370)
eopXD Sep 1, 2026
a1ad3ed
[None][fix] register beneficial-to-skip contributions only after sche…
eopXD Sep 1, 2026
f04859d
[None][infra] Waive 1 failed cases for main in pre-merge 57755 (#18499)
trtllm-agent Sep 1, 2026
e6f2e3f
[None][infra] Waive 8 failed cases for main in post-merge 2942 (#18512)
trtllm-agent Sep 1, 2026
f152eb2
[https://nvbugs/6697142][fix] Wire the stub the way `TrtllmAttention.…
trtllm-agent Sep 1, 2026
8355ecf
[TRTLLM-15405][refactor] Remove the C++ decoder stack behind TRTLLMSa…
zhaoyangwang-nvidia Sep 1, 2026
8c0d0cb
[None][perf] Merge per-iteration attention-DP host allgathers in inpu…
qiaoxj07 Sep 1, 2026
9078952
[None][infra] Waive 1 failed cases for main in pre-merge 57818 (#18522)
trtllm-agent Sep 1, 2026
a434184
[None][infra] Waive 1 failed cases for main in pre-merge 57863 (#18529)
trtllm-agent Sep 1, 2026
efcf8e9
[None][infra] Waive 1 failed cases for main in pre-merge 57863 (#18530)
trtllm-agent Sep 1, 2026
6507185
[None][fix] Support MiniMax-M3 vision meta init (#18466)
peihu-nv Sep 1, 2026
131cd15
[https://nvbugs/6657468][fix] Set UCX_TLS for GB300 in disagg logprob…
moraxu Sep 1, 2026
5fb6883
[https://nvbugs/6699646][fix] Preserve prepared Cosmos3 video frames …
ishovkun Sep 1, 2026
0f94be2
[TRTLLM-15035][test] Wire Kimi K3 spec-dec and suffix-automaton tests…
moraxu Sep 1, 2026
d105e6a
[https://nvbugs/6608382][test] Mitigate disagg cancellation test hang…
chienchunhung Sep 1, 2026
e00d95f
[None][fix] use prompt lookahead for MTP Eagle chunked prefill (#18295)
yizhang-nv Sep 1, 2026
5c03a51
[None][perf] Cache FMHA library selection in TrtllmAttention (#18350)
yuxianq Sep 1, 2026
1c7d1c0
[https://nvbugs/6705034][test] waive Kimi KDA empty prefill test on B…
Mgluhovskoi Sep 1, 2026
b7c5862
[https://nvbugs/6681216][fix] Raise disagg nixl readiness timeout on …
brnguyen2 Sep 1, 2026
c2467bc
[None][feat] Add locality domain Python layer (#18317)
zhangcl Sep 1, 2026
e9376f8
[https://nvbugs/6633931][fix] Size the SM90 fp8 block-scale MoE works…
pranav-nvidia Sep 1, 2026
d147336
[None][perf] Optimize MiniMax-M3 MXFP8 GEMMs (#17238)
peihu-nv Sep 1, 2026
f77d1a2
[None][feat] Add NVFP4 as a cold-page KV Cache Compression Method (#1…
Hudayday Sep 1, 2026
8cbfd0e
[https://nvbugs/6661914][fix] restore Wan 5B per-token AdaLN with Tea…
chang-l Sep 1, 2026
f88f83b
[TRTLLM-12680][fix] stabilize telemetry lifecycle follow-ups (#18454)
Mgluhovskoi Sep 1, 2026
fcc8454
[TRTLLMINF-372][infra] BoltProfileGen: parallel chunked artifact down…
mlefeb01 Sep 1, 2026
181f726
[TRTLLM-15316][feat] Rubin trtllmgen batchedGemm MoE (#17707)
farazkh80 Sep 2, 2026
870d460
[None][perf] Widen MiniMax-M3 decode q in-register instead of in a co…
brb-nv Sep 2, 2026
fa8a3c8
[None][infra] Waive 1 failed cases for main in pre-merge 57886 (#18562)
trtllm-agent Sep 2, 2026
f03e771
[None][test] Unwaive qwen3.5 test cases (#18511)
nv-guomingz Sep 2, 2026
f221314
[None][infra] Waive 1 failed cases for main in pre-merge 57819 (#18567)
trtllm-agent Sep 2, 2026
16881d4
[TRTLLM-15498][perf] optimize Kimi KDA decode data flow (#18251)
jiaganc Sep 2, 2026
5a1ae8f
[None][fix] Minimize and account for attention-DP dummy tokens (#18308)
liji-nv Sep 2, 2026
84a59d6
[https://nvbugs/6633931][fix] Chunk the MoE workspace on the SM90 bra…
pranav-nvidia Sep 2, 2026
1ed2928
[TRTLLM-15040][test] Prune legacy Llama and Nemotron tests (#17858)
xinhe-nv Sep 2, 2026
55b3830
[None][infra] Expand CBTS Tier 2 pilot to QA team (#18442)
crazydemo Sep 2, 2026
08cc100
[None][fix] Enforce the count-crossing invariant in the self-sampling…
zkyue Sep 2, 2026
9291052
[None][test] Enable warmup request for disagg e2e and ctx_only perf s…
chenfeiz0326 Sep 2, 2026
f8aa81a
[https://nvbugs/6698723][fix] Unwaive tests after model config fix (#…
ZhanruiSunCh Sep 2, 2026
0699c4b
[https://nvbugs/6467691][fix] Raise Starlette security floor (#17650)
BowenFu Sep 2, 2026
c74f8cf
[TRTLLM-14575][perf] Fuse DSA decode metadata into a single Triton ke…
xwang233 Sep 2, 2026
d7d79c3
[TRTLLM-14575][perf] Enable fused-A GEMM for the GLM MLA A-projection…
xwang233 Sep 2, 2026
0c30590
[None][test] Add coverage for KimiLinearForCausalLM._setup_helix_mapp…
StanleySun639 Sep 2, 2026
cbd3dcb
[https://nvbugs/6668807][fix] Remove invalid GLM KV cache assertion (…
yizhang-nv Sep 2, 2026
08ebfb8
[None][chore] Remove AutoDeploy (ad-) skills and agents (#18572)
kaiyux Sep 2, 2026
b387759
[None][infra] Auto-update test durations from OpenSearch (last 7 days)
tensorrt-cicd Sep 2, 2026
d0bb5ce
[TRTLLM-14867][feat] Auto-tuning for split-K in LoRA grouped GEMM (#1…
AlessioNetti Sep 2, 2026
6d10c67
[None][fix] Fix INFRA-DEFER stage status and multi-GPU blocking (#18305)
ZhanruiSunCh Sep 2, 2026
5313446
[None][doc] Split LLM API reference into smaller searchable pages (#1…
chzblych Sep 2, 2026
16354ee
[None][perf] Emission-assisted GVR top-K decode for the DeepSeek V4 i…
siyidNV Sep 2, 2026
35b90c1
[TRTLLMINF-353][infra] add maintenance stage config (#18508)
hanjingtian Sep 2, 2026
5098fbe
[None][infra] Tighten CBTS testdef anchors for deletion-only test dif…
yufeiwu-nv Sep 2, 2026
acc5633
[TRTLLMINF-160][infra] Support CBTS test result reuse (#18073)
hanjingtian Sep 2, 2026
24a5c64
[TRTLLM-15889][fix] Proper lazy import for MPI worker submit (#18284)
tongyuantongyu Sep 2, 2026
f848ecb
[https://nvbugs/6602094][fix] Avoid MPI bootstrap in RocketKV unit te…
lfr-0531 Sep 2, 2026
ca38e9e
[TRTLLM-14715][feat] preserve native MoE A2A graph VAs across restore…
hhzhang16 Sep 2, 2026
42903f9
[TRTLLM-15498][perf] prepare Kimi K3 prefill metadata (#18064)
jiaganc Sep 2, 2026
e34e02f
[TRTLLM-15888][fix] Proper lazy import for post transform profile mat…
tongyuantongyu Sep 2, 2026
ef567dd
[None][fix] Fix Qwen3.8-27B NVFP4 checkpoint loading (#18387)
jupiterepoch Sep 2, 2026
e34a4ff
[TRTLLM-12499][feat] Pipelined KVCache transfer for disaggregated ser…
athena-nv Sep 2, 2026
e5f853f
[None][feat] Add Rubin SM107 CuTe DSL foundation and BF16 kernels (#1…
farazkh80 Sep 2, 2026
395985c
[TRTLLM-15448][perf] Implement rank-striped checkpoint read-ahead (#1…
chienchunhung Sep 2, 2026
05b0324
[TRTLLM-14959][refactor] declare MoE backend capabilities instead of …
xxi-nv Sep 2, 2026
777a2c7
[https://nvbugs/6693989][fix] Apply the K3 prompt-token offset only w…
trtllm-agent Sep 2, 2026
2d80f64
[TRTLLMINF-373][infra] BoltProfileGen: persistent version-keyed llvm-…
mlefeb01 Sep 2, 2026
449d5ee
[TRTLLMINF-374][infra] BoltProfileGen: log SLURM queue-vs-run timing …
mlefeb01 Sep 2, 2026
6d3c689
[None][ci] waive pre-existing test failures on main (#18460)
brnguyen2 Sep 2, 2026
30316da
[TRTLLM-15316][feat] Fix fused mHC Phase-4 coherence and support unev…
farazkh80 Sep 2, 2026
cf1f67c
Label paged attention flag as a snippet
thorjohnsen Sep 11, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
The diff you're trying to view is too large. We only load the first 3000 changed files.
1 change: 0 additions & 1 deletion .claude/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,7 +62,6 @@ short and not repeat it.

| Prefix | Domain | Definition |
|---|---|---|
| `ad-` | AutoDeploy | Model onboarding, pipeline debugging, and execution for the AutoDeploy backend |
| `exec-` | Execution infra | Environment setup and job execution (compile, run, container) |
| `kernel-` | Kernel development | Kernel writing, generation, and kernel-specific transforms |
| `perf-` | Performance work | Profiling, analysis, and tuning above the kernel layer (kernel modifications belong under `kernel-`) |
Expand Down
95 changes: 0 additions & 95 deletions .claude/agents/ad-conf-check-update.md
View file
Open in desktop

This file was deleted.

85 changes: 0 additions & 85 deletions .claude/agents/ad-debug-agent.md
View file
Open in desktop

This file was deleted.

Loading
Loading