Skip to content

Pull requests: ROCm/vllm

New pull request New
24 Open 257 Closed
24 Open 257 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

use CK FA for glm-4v on navi3
#281 opened Nov 15, 2024 by jfactory07 Loading…
2
CUDA compilation fix
#278 opened Nov 14, 2024 by hliuca Loading…
Add vectorized rms_norm support for Navi31
#273 opened Nov 12, 2024 by hyoon1 Loading…
3
[Misc] Upload a shell for bare-metal
#268 opened Nov 8, 2024 by Concurrensee Loading…
2
[Kernel] Upload a MoE config file for Mixtral8x7B 8GPU on AMD_Instinct_MI300X_OAM machine (fp16)
#261 opened Nov 4, 2024 by Jacob0226 Loading…
3
[OPT] improve rms_norm kernel
#258 opened Nov 1, 2024 by kkHuang-amd Loading…
23
Fix kernel cache miss and add RDNA configs
#246 opened Oct 25, 2024 by hyoon1 Loading…
9
Fused ROPE and reshape cache kernel
#229 opened Oct 11, 2024 by maleksan85 Loading…
Update run-amd-test.sh
#192 opened Sep 17, 2024 by Alexei-V-Ivanov-AMD Loading…
1
multi-gpu fused_moe tuning support
#143 opened Aug 16, 2024 by divakar-amd Loading…
1 task done
@divakar-amd
8
[DO NOT MERGE] Vinayak/moe final hashem stale
#127 opened Aug 11, 2024 by carlushuang Loading…
1
[DO NOT MERGE] patch wvSpltK_fused_moe from https://github.com/amd-hhashemi/vllm/tre… stale
#126 opened Aug 10, 2024 by carlushuang Loading…
1
Add max-batch-size to benchmark_throughput.py stale
#122 opened Aug 7, 2024 by dllehr-amd Loading…
1
Add truncate to all files after json dump stale
#117 opened Aug 2, 2024 by jpvillam-amd Loading…
@jpvillam-amd
1
[Misc] Use main triton branch
#115 opened Aug 1, 2024 by binarman Loading…
1
Adding SHM broadcast to ROCm/vllm stale
#113 opened Jul 31, 2024 by Lzy17 Loading…
1
optimizations for process output step stale
#104 opened Jul 25, 2024 by sanyalington Loading…
1
Update QueueLLM stale
#97 opened Jul 22, 2024 by gyulaz-htec Loading…
1
Add benchmark_latency_batched.py stale
#96 opened Jul 22, 2024 by dllehr-amd Loading…
3
New LLM for MLPerf Server scenario serving stale
#94 opened Jul 19, 2024 by gyulaz-htec Loading…
1
Update LLM and AsyncLLM to expose more functionality stale
#91 opened Jul 18, 2024 by gyulaz-htec Loading…
1
Update LLM and AsyncLLM to expose more functionality stale
#90 opened Jul 18, 2024 by gyulaz-htec Loading…
1
Add VLLM_SCHED_PREFILL_KVC_FREEPCT stale
#89 opened Jul 18, 2024 by sanyalington Loading…
2
Update on naive_attn module
#21 opened May 28, 2024 by seungrokj Loading…
ProTip! Mix and match filters to narrow down what you’re looking for.