Skip to content

[Handoff to @Oseltamivir Claude /loop] [Klaud Cold] Update qwen3.5-fp4-b300-sglang (+mtp) SGLang image to v0.5.12-cu130 #1475

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

Open
functionstackx wants to merge 6 commits into
base: main
Choose a base branch
from
+12 −4
Open

[Handoff to @Oseltamivir Claude /loop] [Klaud Cold] Update qwen3.5-fp4-b300-sglang (+mtp) SGLang image to v0.5.12-cu130 #1475

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
f8ba0a8
Update qwen3.5-fp4-b300-sglang (+mtp) SGLang image to v0.5.12-cu130
functionstackx May 18, 2026
2562dd5
chore: fill pr-link for #1475
functionstackx May 18, 2026
108982c
fix(qwen3.5_fp4_b300): use --mm-attention-backend triton_attn
May 18, 2026
1490f59
Merge remote-tracking branch 'origin/main' into HEAD
May 18, 2026
6ff1a34
Re-trigger sweep (previous Run Sweep run stuck pending with 0 jobs)
May 18, 2026
bfac96d
Merge remote-tracking branch 'origin/main' into HEAD
May 18, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions .github/configs/nvidia-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2435,7 +2435,7 @@ qwen3.5-fp8-b300-sglang:
- { tp: 4, ep: 1, conc-start: 4, conc-end: 256 }

qwen3.5-fp4-b300-sglang:
image: lmsysorg/sglang:v0.5.11-cu130
image: lmsysorg/sglang:v0.5.12-cu130
model: nvidia/Qwen3.5-397B-A17B-NVFP4
model-prefix: qwen3.5
runner: b300
Expand All @@ -2456,7 +2456,7 @@ qwen3.5-fp4-b300-sglang:
- { tp: 2, ep: 2, conc-start: 4, conc-end: 128 }

qwen3.5-fp4-b300-sglang-mtp:
image: lmsysorg/sglang:v0.5.11-cu130
image: lmsysorg/sglang:v0.5.12-cu130
model: nvidia/Qwen3.5-397B-A17B-NVFP4
model-prefix: qwen3.5
runner: b300
Expand Down
2 changes: 1 addition & 1 deletion benchmarks/single_node/qwen3.5_fp4_b300.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,7 +73,7 @@ PYTHONNOUSERSITE=1 python3 -m sglang.launch_server --model-path=$MODEL --host=0.
--cuda-graph-max-bs $CUDA_GRAPH_MAX_BATCH_SIZE --max-running-requests $MAX_RUNNING_REQUESTS \
--mem-fraction-static $MEM_FRAC_STATIC --chunked-prefill-size $CHUNKED_PREFILL_SIZE --max-prefill-tokens $MAX_PREFILL_TOKENS \
--context-length $CONTEXT_LENGTH --disable-radix-cache \
--attention-backend trtllm_mha --moe-runner-backend flashinfer_trtllm \
--attention-backend trtllm_mha --mm-attention-backend triton_attn --moe-runner-backend flashinfer_trtllm \
$EXTRA_ARGS --scheduler-recv-interval $SCHEDULER_RECV_INTERVAL \
--tokenizer-worker-num 6 --stream-interval 30 > $SERVER_LOG 2>&1 &

Expand Down
2 changes: 1 addition & 1 deletion benchmarks/single_node/qwen3.5_fp4_b300_mtp.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,7 +73,7 @@ PYTHONNOUSERSITE=1 python3 -m sglang.launch_server --model-path=$MODEL --host=0.
--cuda-graph-max-bs $CUDA_GRAPH_MAX_BATCH_SIZE --max-running-requests $MAX_RUNNING_REQUESTS \
--mem-fraction-static $MEM_FRAC_STATIC --chunked-prefill-size $CHUNKED_PREFILL_SIZE --max-prefill-tokens $MAX_PREFILL_TOKENS \
--context-length $CONTEXT_LENGTH --disable-radix-cache \
--attention-backend trtllm_mha --moe-runner-backend flashinfer_trtllm \
--attention-backend trtllm_mha --mm-attention-backend triton_attn --moe-runner-backend flashinfer_trtllm \
$EXTRA_ARGS --scheduler-recv-interval $SCHEDULER_RECV_INTERVAL \
--tokenizer-worker-num 6 --stream-interval 30 \
--speculative-algorithm EAGLE \
Expand Down
8 changes: 8 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2820,3 +2820,11 @@
description:
- "Update TensorRT-LLM image from v1.3.0rc11 (34d old) to v1.3.0rc14 (latest pre-release)"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1491

- config-keys:
- qwen3.5-fp4-b300-sglang
- qwen3.5-fp4-b300-sglang-mtp
description:
- "Update SGLang image from v0.5.11-cu130 (5d old) to v0.5.12-cu130"
- "Add --mm-attention-backend triton_attn to bypass flash-attn cute sm_103 assertion (see sgl-project/sglang#25564)"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1475
Loading