docs:add torch flow supported model list. #4129
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: nv-guomingz <[email protected]>
|
/bot skip --comment "docs only" |
|
PR_Github #4412 [ skip ] triggered by Bot |
|
PR_Github #4412 [ skip ] completed with state |
chzblych
approved these changes
May 8, 2025
dcampora
pushed a commit
to dcampora/tensorrt_llm
that referenced
this pull request
May 16, 2025
Signed-off-by: nv-guomingz <[email protected]>
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]>
nv-guomingz
deleted the
user/guomingz/doc_update_torch_support_matrix
branch
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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.