Skip to content
This repository was archived by the owner on Apr 20, 2026. It is now read-only.

Fix config for 1k/8k #94

Merged
ishandhanani merged 2 commits into from
Jan 23, 2026
Merged

Fix config for 1k/8k #94

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a2a2413
Fix config for 1k/8k
kyleliang-nv Jan 23, 2026
0c27e33
Revert modelname change
kyleliang-nv Jan 23, 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
2 changes: 1 addition & 1 deletion recipies/gb200-fp4/1k8k/low-latency.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@ name: "gb200-fp4-1p2d"

model:
path: "dsr1"
container: "lmsysorg/sglang:dev-cu13"
container: "lmsysorg/sglang:nightly-dev-cu13-20260121-1e309030"
precision: "fp4"

resources:
Expand Down
4 changes: 2 additions & 2 deletions recipies/gb200-fp4/1k8k/max-tpt.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ name: "gb200-fp4-max-tpt"

model:
path: "dsr1"
container: "lmsysorg/sglang:dev-cu13"
container: "lmsysorg/sglang:nightly-dev-cu13-20260121-1e309030"
precision: "fp4"

resources:
Expand Down Expand Up @@ -55,7 +55,6 @@ backend:
SGLANG_DISABLE_TP_MEMORY_INBALANCE_CHECK: "1"
SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK: "1024"
SGLANG_MOE_NVFP4_DISPATCH: "1"
SGLANG_FLASHINFER_FP4_GEMM_BACKEND: "cutlass"

sglang_config:
prefill:
Expand Down Expand Up @@ -230,6 +229,7 @@ backend:
enable-dp-lm-head: true
prefill-round-robin-balance: true
enable-dp-attention: true
fp4-gemm-backend: "flashinfer_cutlass"

# Parallelism
tp-size: 48
Expand Down
4 changes: 2 additions & 2 deletions recipies/gb200-fp4/1k8k/mid-curve.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ name: "gb200-fp4-max-tpt-2"

model:
path: "dsr1"
container: "lmsysorg/sglang:dev-cu13"
container: "lmsysorg/sglang:nightly-dev-cu13-20260121-1e309030"
precision: "fp4"

resources:
Expand Down Expand Up @@ -56,7 +56,6 @@ backend:
SGLANG_DISABLE_TP_MEMORY_INBALANCE_CHECK: "1"
SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK: "1024"
SGLANG_MOE_NVFP4_DISPATCH: "1"
SGLANG_FLASHINFER_FP4_GEMM_BACKEND: "cutlass"

sglang_config:
prefill:
Expand Down Expand Up @@ -230,6 +229,7 @@ backend:
enable-dp-lm-head: true
prefill-round-robin-balance: true
enable-dp-attention: true
fp4-gemm-backend: "flashinfer_cutlass"

# Parallelism
tp-size: 32
Expand Down
Loading