Skip to content

Conversation

nv-guomingz
Copy link
Collaborator

Per discussion with @juney-nvidia , we'd like to make supported model list of torch flow more explicitly for users to access in the generated doc site rather than deeply embedded into the README only.

@nv-guomingz nv-guomingz requested a review from a team as a code owner May 7, 2025 16:56
@nv-guomingz nv-guomingz requested a review from kaiyux May 7, 2025 16:56
@nv-guomingz
Copy link
Collaborator Author

/bot skip --comment "docs only"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4412 [ skip ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #4412 [ skip ] completed with state SUCCESS
Skipping testing for commit 128fba0

@chzblych chzblych merged commit 9727aae into NVIDIA:release/0.19 May 8, 2025
3 checks passed
dcampora pushed a commit to dcampora/tensorrt_llm that referenced this pull request May 16, 2025
dcampora added a commit that referenced this pull request May 16, 2025
* fix: Fix/fused moe 0.19 (#3799)

* fix bug of stream init

Signed-off-by: bhsueh <[email protected]>

* fix bug

Signed-off-by: bhsueh <[email protected]>

---------

Signed-off-by: bhsueh <[email protected]>

* fix: Add pre-download of checkpoint before benchmark. (#3772)

* Add pre-download of checkpoint before benchmark.

Signed-off-by: Frank Di Natale <[email protected]>

* Add missing remote code flag.

Signed-off-by: Frank Di Natale <[email protected]>

* Move from_pretrained to throughput benchmark.

Signed-off-by: Frank Di Natale <[email protected]>

* Move download and use snapshot_download.

Signed-off-by: Frank Di Natale <[email protected]>

* Removed trusted flag.

Signed-off-by: Frank Di Natale <[email protected]>

* Fix benchmark command in iteration log test.

Signed-off-by: Frank Di Natale <[email protected]>

---------

Signed-off-by: Frank Di Natale <[email protected]>

* [https://nvbugspro.nvidia.com/bug/5241495][fix] CUDA Graph padding with overlap scheduler (#3839)

* fix

Signed-off-by: Enwei Zhu <[email protected]>

* fuse

Signed-off-by: Enwei Zhu <[email protected]>

* fix

Signed-off-by: Enwei Zhu <[email protected]>

* fix

Signed-off-by: Enwei Zhu <[email protected]>

---------

Signed-off-by: Enwei Zhu <[email protected]>

* TRTLLM-4875 feat: Add version switcher to doc (#3871)

Signed-off-by: Kaiyu Xie <[email protected]>

* waive a test (#3897)

Signed-off-by: Superjomn <[email protected]>

* docs:fix https://nvbugs/5244616 by removing new invalid links. (#3939)

Signed-off-by: nv-guomingz <[email protected]>
Co-authored-by: nv-guomingz <[email protected]>

* fix: remote mpi session abort (#3884)

* fix remote mpi session

Signed-off-by: Superjomn <[email protected]>

* fix

Signed-off-by: Superjomn <[email protected]>

---------

Signed-off-by: Superjomn <[email protected]>

* skip fp8 gemm for pre-hopper (#3931)

Signed-off-by: Ivy Zhang <[email protected]>

* [https://nvbugspro.nvidia.com/bug/5247148][fix] Attention DP with overlap scheduler (#3975)

* fix

Signed-off-by: Enwei Zhu <[email protected]>

* update multigpu list

Signed-off-by: Enwei Zhu <[email protected]>

* fix namings

Signed-off-by: Enwei Zhu <[email protected]>

---------

Signed-off-by: Enwei Zhu <[email protected]>

* Doc: Fix H200 DeepSeek R1 perf doc (#4006)

* fix doc

Signed-off-by: jiahanc <[email protected]>

* update perf number

Signed-off-by: jiahanc <[email protected]>

---------

Signed-off-by: jiahanc <[email protected]>

* Fix the perf regression caused by insufficient cache warmup. (#4042)

Force tuning up to 8192 sequence length for NVFP4 linear op. Also, make this runtime-selectable with UB enabled.

Signed-off-by: Yukun He <[email protected]>

* doc: Update 0.19.0 release notes (#3976)

Signed-off-by: Kaiyu Xie <[email protected]>

* Optimize the AutoTuner cache access code to reduce host code overhead. (#4060)

The NVFP4 Linear op is very sensitive to the host overhead.
This PR introduces customizable `find_nearest_profile` and `get_cache_key_specifc`, which allow users to override the default method for generating the cache key.

Signed-off-by: Yukun He <[email protected]>

* Update switcher (#4098)

Signed-off-by: Kaiyu Xie <[email protected]>

* doc: update release notes (#4108)

Signed-off-by: Kaiyu Xie <[email protected]>

* docs:update 0.19 doc. (#4120)

Signed-off-by: nv-guomingz <[email protected]>

* docs:add torch flow supported model list. (#4129)

Signed-off-by: nv-guomingz <[email protected]>

* doc: Release V0.19 Perf Overview Update (#4166)

Signed-off-by: zpatel <[email protected]>

* Fix readme of autodeploy.

Signed-off-by: Daniel Campora <[email protected]>

* Update tensorrt_llm/_torch/pyexecutor/llm_request.py

Co-authored-by: Enwei Zhu <[email protected]>
Signed-off-by: Daniel Cámpora <[email protected]>

* Revert mgmn worker node.

Signed-off-by: Daniel Campora <[email protected]>

* Change to disable_overlap_scheduler.

Signed-off-by: Daniel Campora <[email protected]>

---------

Signed-off-by: bhsueh <[email protected]>
Signed-off-by: Frank Di Natale <[email protected]>
Signed-off-by: Enwei Zhu <[email protected]>
Signed-off-by: Kaiyu Xie <[email protected]>
Signed-off-by: Superjomn <[email protected]>
Signed-off-by: nv-guomingz <[email protected]>
Signed-off-by: Ivy Zhang <[email protected]>
Signed-off-by: jiahanc <[email protected]>
Signed-off-by: Yukun He <[email protected]>
Signed-off-by: nv-guomingz <[email protected]>
Signed-off-by: zpatel <[email protected]>
Signed-off-by: Daniel Campora <[email protected]>
Signed-off-by: Daniel Cámpora <[email protected]>
Co-authored-by: bhsueh_NV <[email protected]>
Co-authored-by: Frank <[email protected]>
Co-authored-by: Enwei Zhu <[email protected]>
Co-authored-by: Kaiyu Xie <[email protected]>
Co-authored-by: Yan Chunwei <[email protected]>
Co-authored-by: nv-guomingz <[email protected]>
Co-authored-by: nv-guomingz <[email protected]>
Co-authored-by: Ivy Zhang <[email protected]>
Co-authored-by: jiahanc <[email protected]>
Co-authored-by: Yukun He <[email protected]>
Co-authored-by: Zac Patel <[email protected]>
Copy link

@addiwani32 addiwani32 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Good

@nv-guomingz nv-guomingz deleted the user/guomingz/doc_update_torch_support_matrix branch September 30, 2025 07:57
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants