Skip to content

[on june 22, 2026, current gptoss submiters were given notice that it will be deprepcated on july 6th, and were given an chance for comment period and everyone reacted notice] Deprecate gpt-oss-120b benchmark configs / 弃用 gpt-oss-120b 基准测试配置 #2101

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

Merged
functionstackx merged 1 commit into from
Jul 6, 2026
Merged

[on june 22, 2026, current gptoss submiters were given notice that it will be deprepcated on july 6th, and were given an chance for comment period and everyone reacted notice] Deprecate gpt-oss-120b benchmark configs / 弃用 gpt-oss-120b 基准测试配置 #2101

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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 ...multi_node/gptoss_fp4_gb200_dynamo-trt.sh → ...deprecated/gptoss_fp4_gb200_dynamo-trt.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

set -x

source "$(dirname "$0")/../benchmark_lib.sh"
source "$(dirname "$0")/../../benchmark_lib.sh"

check_env_vars \
CONC_LIST \
Expand Down
2 changes: 1 addition & 1 deletion ...gle_node/fixed_seq_len/gptoss_fp4_b200.sh → ...xed_seq_len/deprecated/gptoss_fp4_b200.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
#!/usr/bin/env bash

source "$(dirname "$0")/../../benchmark_lib.sh"
source "$(dirname "$0")/../../../benchmark_lib.sh"

check_env_vars \
MODEL \
Expand Down
2 changes: 1 addition & 1 deletion ...node/fixed_seq_len/gptoss_fp4_b200_trt.sh → ...seq_len/deprecated/gptoss_fp4_b200_trt.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
#!/usr/bin/env bash

# Source benchmark utilities early
source "$(dirname "$0")/../../benchmark_lib.sh"
source "$(dirname "$0")/../../../benchmark_lib.sh"

check_env_vars \
MODEL \
Expand Down
2 changes: 1 addition & 1 deletion ...gle_node/fixed_seq_len/gptoss_fp4_h100.sh → ...xed_seq_len/deprecated/gptoss_fp4_h100.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
#!/usr/bin/env bash

source "$(dirname "$0")/../../benchmark_lib.sh"
source "$(dirname "$0")/../../../benchmark_lib.sh"

check_env_vars \
MODEL \
Expand Down
2 changes: 1 addition & 1 deletion ...gle_node/fixed_seq_len/gptoss_fp4_h200.sh → ...xed_seq_len/deprecated/gptoss_fp4_h200.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
#!/usr/bin/env bash

source "$(dirname "$0")/../../benchmark_lib.sh"
source "$(dirname "$0")/../../../benchmark_lib.sh"

check_env_vars \
MODEL \
Expand Down
2 changes: 1 addition & 1 deletion ...node/fixed_seq_len/gptoss_fp4_h200_trt.sh → ...seq_len/deprecated/gptoss_fp4_h200_trt.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
#!/usr/bin/env bash

source "$(dirname "$0")/../../benchmark_lib.sh"
source "$(dirname "$0")/../../../benchmark_lib.sh"

check_env_vars \
MODEL \
Expand Down
2 changes: 1 addition & 1 deletion ...e_node/fixed_seq_len/gptoss_fp4_mi300x.sh → ...d_seq_len/deprecated/gptoss_fp4_mi300x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
#!/usr/bin/env bash

source "$(dirname "$0")/../../benchmark_lib.sh"
source "$(dirname "$0")/../../../benchmark_lib.sh"

check_env_vars \
MODEL \
Expand Down
2 changes: 1 addition & 1 deletion ...e_node/fixed_seq_len/gptoss_fp4_mi325x.sh → ...d_seq_len/deprecated/gptoss_fp4_mi325x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
#!/usr/bin/env bash

source "$(dirname "$0")/../../benchmark_lib.sh"
source "$(dirname "$0")/../../../benchmark_lib.sh"

check_env_vars \
MODEL \
Expand Down
2 changes: 1 addition & 1 deletion ...e_node/fixed_seq_len/gptoss_fp4_mi355x.sh → ...d_seq_len/deprecated/gptoss_fp4_mi355x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
#!/usr/bin/env bash

source "$(dirname "$0")/../../benchmark_lib.sh"
source "$(dirname "$0")/../../../benchmark_lib.sh"

check_env_vars \
MODEL \
Expand Down
2 changes: 1 addition & 1 deletion ...e/fixed_seq_len/gptoss_fp4_mi355x_atom.sh → ..._len/deprecated/gptoss_fp4_mi355x_atom.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
#!/usr/bin/env bash

source "$(dirname "$0")/../../benchmark_lib.sh"
source "$(dirname "$0")/../../../benchmark_lib.sh"

check_env_vars \
MODEL \
Expand Down
104 changes: 0 additions & 104 deletions configs/amd-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -304,7 +304,6 @@ qwen3.5-fp8-mi355x-sglang-agentic:
- search-space:
- { tp: 8, ep: 1, kv-offloading: none, conc-list: [1, 2, 4, 8, 16, 32] }


qwen3.5-fp8-mi355x-atom:
image: rocm/atom:rocm7.2.3_ubuntu24.04_py3.12_pytorch_release_2.10.0_atom20260511
model: Qwen/Qwen3.5-397B-A17B-FP8
Expand Down Expand Up @@ -809,7 +808,6 @@ kimik2.5-fp4-mi355x-vllm-agentic:
- { tp: 4, kv-offloading: none, conc-list: [16, 24, 32, 40] }
- { tp: 4, kv-offloading: dram, kv-offload-backend: native, conc-list: [16, 24, 32, 40] }


kimik2.5-fp4-mi355x-atom:
image: rocm/atom:rocm7.2.3_ubuntu24.04_py3.12_pytorch_release_2.10.0_atom20260511
model: amd/Kimi-K2.5-MXFP4
Expand All @@ -831,100 +829,6 @@ kimik2.5-fp4-mi355x-atom:
- { tp: 8, conc-start: 4, conc-end: 128 }
- { tp: 4, conc-start: 4, conc-end: 128 }

gptoss-fp4-mi300x-vllm:
image: vllm/vllm-openai-rocm:v0.17.0
model: openai/gpt-oss-120b
model-prefix: gptoss
runner: mi300x
precision: fp4
framework: vllm
multinode: false
scenarios:
fixed-seq-len:
- isl: 1024
osl: 1024
search-space:
- { tp: 1, conc-start: 64, conc-end: 256 }
- { tp: 2, conc-start: 4, conc-end: 64 }
- { tp: 4, conc-start: 4, conc-end: 64 }
- { tp: 8, conc-start: 1, conc-end: 16 }
- isl: 8192
osl: 1024
search-space:
- { tp: 1, conc-start: 4, conc-end: 64 }
- { tp: 2, conc-start: 4, conc-end: 64 }
- { tp: 4, conc-start: 4, conc-end: 64 }
- { tp: 8, conc-start: 1, conc-end: 16 }

gptoss-fp4-mi325x-vllm:
image: vllm/vllm-openai-rocm:v0.22.0
model: openai/gpt-oss-120b
model-prefix: gptoss
runner: mi325x
precision: fp4
framework: vllm
multinode: false
scenarios:
fixed-seq-len:
- isl: 1024
osl: 1024
search-space:
- { tp: 1, conc-start: 4, conc-end: 64 }
- { tp: 2, conc-start: 4, conc-end: 64 }
- { tp: 4, conc-start: 4, conc-end: 64 }
- { tp: 8, conc-start: 4, conc-end: 64 }
- isl: 8192
osl: 1024
search-space:
- { tp: 1, conc-start: 4, conc-end: 64 }
- { tp: 2, conc-start: 4, conc-end: 8 }
- { tp: 4, conc-start: 4, conc-end: 8 }
- { tp: 8, conc-start: 4, conc-end: 16 }

gptoss-fp4-mi355x-vllm:
image: vllm/vllm-openai-rocm:v0.22.0
model: openai/gpt-oss-120b
model-prefix: gptoss
runner: mi355x
precision: fp4
framework: vllm
multinode: false
scenarios:
fixed-seq-len:
- isl: 1024
osl: 1024
search-space:
- { tp: 1, conc-start: 4, conc-end: 128 }
- { tp: 4, conc-start: 4, conc-end: 8 }
- { tp: 8, conc-start: 4, conc-end: 16 }
- isl: 8192
osl: 1024
search-space:
- { tp: 1, conc-start: 4, conc-end: 128 }
- { tp: 4, conc-start: 4, conc-end: 4 }
- { tp: 8, conc-start: 4, conc-end: 8 }

gptoss-fp4-mi355x-atom:
image: rocm/atom:rocm7.2.2_ubuntu24.04_py3.12_pytorch_release_2.10.0_atom0.1.2.post
model: openai/gpt-oss-120b
model-prefix: gptoss
runner: mi355x
precision: fp4
framework: atom
multinode: false
scenarios:
fixed-seq-len:
- isl: 1024
osl: 1024
search-space:
- { tp: 1, conc-start: 16, conc-end: 256 }
- { tp: 8, ep: 1, conc-start: 4, conc-end: 32 }
- isl: 8192
osl: 1024
search-space:
- { tp: 1, conc-start: 4, conc-end: 256 }
- { tp: 8, ep: 1, conc-start: 4, conc-end: 16 }

dsr1-fp8-mi355x-atom:
image: rocm/atom:rocm7.2.3_ubuntu24.04_py3.12_pytorch_release_2.10.0_atom20260511
model: deepseek-ai/DeepSeek-R1-0528
Expand Down Expand Up @@ -1664,7 +1568,6 @@ dsr1-fp4-mi355x-sglang-disagg-1k1k-mtp:
- "DECODE_NODES=1"
- "DECODE_MTP_SIZE=1"


dsr1-fp4-mi355x-sglang-disagg-8k1k-mtp:
image: lmsysorg/sglang-rocm:v0.5.12.post1-rocm720-mi35x-20260529
model: amd/DeepSeek-R1-0528-MXFP4-v2
Expand Down Expand Up @@ -1775,7 +1678,6 @@ dsr1-fp4-mi355x-sglang-disagg-8k1k-mtp:
- "DECODE_NODES=1"
- "DECODE_MTP_SIZE=3"


# 1*DEP8 + 1*DEP8
- spec-decoding: "mtp"
conc-list: [ 128 ]
Expand Down Expand Up @@ -1856,7 +1758,6 @@ dsv4-fp4-mi355x-sglang:
- { tp: 4, dp-attn: true, conc-start: 16, conc-end: 128 }
- { tp: 4, dp-attn: false, conc-start: 1, conc-end: 32 }


# MTP variant of dsv4-fp4-mi355x-sglang. Mirrors the base search space and adds
# spec-decoding: mtp, which routes to dsv4_fp4_mi355x_sglang_mtp.sh (EAGLE
# speculative decoding), per sgl-project/sglang#26383 ([AMD][DSV4] DSV4 MTP
Expand Down Expand Up @@ -2121,8 +2022,6 @@ qwen3.5-fp8-mi355x-sglang-agentic-hicache:
- { tp: 8, ep: 1, kv-offloading: none, conc-list: [1, 2, 4, 8, 16, 32] }
- { tp: 8, ep: 1, kv-offloading: dram, kv-offload-backend: hicache, conc-list: [16, 32, 48, 64] }



# DSv4-Pro FP4 on MI355X via SGLang. Uses a rocm720 mi35x image built off the
# amd/deepseek_v4 branch in sgl-project/sglang; the SHA is encoded in the
# image tag, so bumping sglang is just an image tag bump here. Sweeps
Expand All @@ -2146,7 +2045,6 @@ dsv4-fp4-mi355x-vllm-agentic:
- { tp: 4, kv-offloading: none, conc-list: [1, 2, 4, 8, 10, 12, 16] }
- { tp: 4, ep: 4, dp-attn: true, kv-offloading: none, conc-list: [16, 24, 32, 40, 48] }


# DSv4-Pro FP4 on MI355X via SGLang. Uses a rocm720 mi35x image built off the
# amd/deepseek_v4 branch in sgl-project/sglang; the SHA is encoded in the
# image tag, so bumping sglang is just an image tag bump here. Sweeps
Expand Down Expand Up @@ -2380,7 +2278,6 @@ dsr1-fp4-mi355x-sglang-disagg-mtp:
- "DECODE_NODES=1"
- "DECODE_MTP_SIZE=1"


# DSv4-Pro FP4 on MI355X via SGLang. Uses a rocm720 mi35x image built off the
# amd/deepseek_v4 branch in sgl-project/sglang; the SHA is encoded in the
# image tag, so bumping sglang is just an image tag bump here. Sweeps
Expand All @@ -2400,7 +2297,6 @@ dsv4-fp4-mi355x-sglang-agentic:
- { tp: 8, kv-offloading: none, conc-list: [16, 32, 64] }
- { tp: 8, dp-attn: true, kv-offloading: none, conc-list: [64, 128, 256] }


# MiniMax-M3 MXFP8 MI355X recipe:
# https://github.com/vllm-project/recipes/commit/2a3728ed9892debfd767a72a58ebc90b33f186e5
# MXFP8 runs from TP=4 on gfx950; block size 128 is mandatory for MSA.
Expand Down
96 changes: 96 additions & 0 deletions configs/deprecated/amd-gptoss-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,96 @@
# Deprecated gpt-oss-120b entries archived from amd-master.yaml.
# Removed from the active master config so sweep generation no longer selects them.

gptoss-fp4-mi300x-vllm:
image: vllm/vllm-openai-rocm:v0.17.0
model: openai/gpt-oss-120b
model-prefix: gptoss
runner: mi300x
precision: fp4
framework: vllm
multinode: false
scenarios:
fixed-seq-len:
- isl: 1024
osl: 1024
search-space:
- { tp: 1, conc-start: 64, conc-end: 256 }
- { tp: 2, conc-start: 4, conc-end: 64 }
- { tp: 4, conc-start: 4, conc-end: 64 }
- { tp: 8, conc-start: 1, conc-end: 16 }
- isl: 8192
osl: 1024
search-space:
- { tp: 1, conc-start: 4, conc-end: 64 }
- { tp: 2, conc-start: 4, conc-end: 64 }
- { tp: 4, conc-start: 4, conc-end: 64 }
- { tp: 8, conc-start: 1, conc-end: 16 }

gptoss-fp4-mi325x-vllm:
image: vllm/vllm-openai-rocm:v0.22.0
model: openai/gpt-oss-120b
model-prefix: gptoss
runner: mi325x
precision: fp4
framework: vllm
multinode: false
scenarios:
fixed-seq-len:
- isl: 1024
osl: 1024
search-space:
- { tp: 1, conc-start: 4, conc-end: 64 }
- { tp: 2, conc-start: 4, conc-end: 64 }
- { tp: 4, conc-start: 4, conc-end: 64 }
- { tp: 8, conc-start: 4, conc-end: 64 }
- isl: 8192
osl: 1024
search-space:
- { tp: 1, conc-start: 4, conc-end: 64 }
- { tp: 2, conc-start: 4, conc-end: 8 }
- { tp: 4, conc-start: 4, conc-end: 8 }
- { tp: 8, conc-start: 4, conc-end: 16 }

gptoss-fp4-mi355x-vllm:
image: vllm/vllm-openai-rocm:v0.22.0
model: openai/gpt-oss-120b
model-prefix: gptoss
runner: mi355x
precision: fp4
framework: vllm
multinode: false
scenarios:
fixed-seq-len:
- isl: 1024
osl: 1024
search-space:
- { tp: 1, conc-start: 4, conc-end: 128 }
- { tp: 4, conc-start: 4, conc-end: 8 }
- { tp: 8, conc-start: 4, conc-end: 16 }
- isl: 8192
osl: 1024
search-space:
- { tp: 1, conc-start: 4, conc-end: 128 }
- { tp: 4, conc-start: 4, conc-end: 4 }
- { tp: 8, conc-start: 4, conc-end: 8 }

gptoss-fp4-mi355x-atom:
image: rocm/atom:rocm7.2.2_ubuntu24.04_py3.12_pytorch_release_2.10.0_atom0.1.2.post
model: openai/gpt-oss-120b
model-prefix: gptoss
runner: mi355x
precision: fp4
framework: atom
multinode: false
scenarios:
fixed-seq-len:
- isl: 1024
osl: 1024
search-space:
- { tp: 1, conc-start: 16, conc-end: 256 }
- { tp: 8, ep: 1, conc-start: 4, conc-end: 32 }
- isl: 8192
osl: 1024
search-space:
- { tp: 1, conc-start: 4, conc-end: 256 }
- { tp: 8, ep: 1, conc-start: 4, conc-end: 16 }
Loading