Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
181 Open 771 Closed
181 Open 771 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

doc: Update perf-benchmarking doc on GPU configuration for consistent benchmarking.
#3458 opened Apr 10, 2025 by bobboli Loading…
test:add fp8_kv_cache functionality test case.
#3457 opened Apr 10, 2025 by nv-guomingz • Draft
fix: Eagle decoding
#3456 opened Apr 10, 2025 by Funatiq Loading…
2
feat/loraOp
#3455 opened Apr 10, 2025 by danielafrimi Loading…
test: Add DeepSeek-V3-Lite PP=4 cases
#3454 opened Apr 10, 2025 by syuoni Loading…
5
feat: draft/Lora op
#3453 opened Apr 10, 2025 by danielafrimi • Draft
chore: add dgx_h200 tests
#3451 opened Apr 10, 2025 by yiqingy0 • Draft
5
chore: Unify Python NVTX call
#3450 opened Apr 10, 2025 by kaiyux Loading…
5
fix: Fix PP for llama.
#3449 opened Apr 10, 2025 by yuxianq Loading…
9
fix: nvbugs/5187237 nvbugs/5112075: fix deterministic mode error
#3448 opened Apr 10, 2025 by VALLIS-NERIA • Draft
2
feat: Update fmha kernels to support Eagle3 on blackwell.
#3446 opened Apr 10, 2025 by PerkzZheng Loading…
8
Feat: Variable-Beam-Width-Search (VBWS) part4
#3445 opened Apr 10, 2025 by wili-65535 • Draft
infra: Support auto trigger test stage for special file change.
#3443 opened Apr 10, 2025 by ZhanruiSunCh Loading…
3
test: move mistral / mixtral test cases in QA test list into the new accuracy test suite
#3440 opened Apr 10, 2025 by crazydemo Loading…
2 tasks
perf: Eliminate the need for attention DP padding when possible Community Engagement Community want to contribute
#3439 opened Apr 10, 2025 by jinyangyuan-nvidia Loading…
@jinyangyuan-nvidia
12
feat: Add group_rms_norm kernel to normalize multiple inputs in a single operator.
#3438 opened Apr 10, 2025 by SimengLiu-nv • Draft
@SimengLiu-nv
6
feat: replace MLA context (192x128 packed) fmha from ampere-style to hopper-style
#3436 opened Apr 10, 2025 by zhou-yuxin • Draft
fix: Fix the issues related to fused moe path.
#3435 opened Apr 10, 2025 by hyukn Loading…
6
infra: always trigger multi gpu test to protect llama and deepseek
#3434 opened Apr 10, 2025 by QiJune Loading…
3
Do not merge, internal
#3431 opened Apr 9, 2025 by milesial • Draft
4
feat: Nemotron-H model support
#3430 opened Apr 9, 2025 by vegaluisjose Loading…
9
chore: unify pp_layers helpers
#3429 opened Apr 9, 2025 by achartier Loading…
9
fix: Fixing issue with first gen token being returned twice in streaming
#3427 opened Apr 9, 2025 by pcastonguay Loading…
9
Feat: Prompt-Lookup-Decoding (PLD) with IFB
#3425 opened Apr 9, 2025 by wili-65535 • Draft
3
feat: Replace cyclic kv cache with sliding kv cache
#3424 opened Apr 9, 2025 by tomeras91 • Draft
12
ProTip! Type g i on any issue or pull request to go back to the issue listing page.