From e8928bc40243a057dd6591d92eecd60f6e31c90c Mon Sep 17 00:00:00 2001 From: Cam Quilici Date: Thu, 15 Oct 2026 10:57:29 -0500 Subject: [PATCH 1/2] fix(agentx): upgrade harness to 1.0.10 for SPAWN worker affinity --- inferencex-e2e/docs/agentx-standalone.md | 4 ++-- inferencex-e2e/infx/bench/agentic/requirements.txt | 2 +- inferencex-e2e/perf-changelog.yaml | 8 ++++++++ 3 files changed, 11 insertions(+), 3 deletions(-) diff --git a/inferencex-e2e/docs/agentx-standalone.md b/inferencex-e2e/docs/agentx-standalone.md index f077c6b46a..59f14a0ea3 100644 --- a/inferencex-e2e/docs/agentx-standalone.md +++ b/inferencex-e2e/docs/agentx-standalone.md @@ -9,10 +9,10 @@ Install the pinned PyPI release in a Python 3.11–3.13 virtual environment: ```bash python3 -m venv .venv-agentx source .venv-agentx/bin/activate -python -m pip install 'agentx-harness==1.0.9' +python -m pip install 'agentx-harness==1.0.10' ``` -The package version matches the `agentx-v1.0.9` GitHub release. The `agentx` +The package version matches the `agentx-v1.0.10` GitHub release. The `agentx` command selects the `agentx` scenario by default. ## Run diff --git a/inferencex-e2e/infx/bench/agentic/requirements.txt b/inferencex-e2e/infx/bench/agentic/requirements.txt index 92db0f2559..be47a354e3 100644 --- a/inferencex-e2e/infx/bench/agentic/requirements.txt +++ b/inferencex-e2e/infx/bench/agentic/requirements.txt @@ -1,2 +1,2 @@ -agentx-harness==1.0.9 +agentx-harness==1.0.10 datasets>=4.7.0 diff --git a/inferencex-e2e/perf-changelog.yaml b/inferencex-e2e/perf-changelog.yaml index e08e5aec18..7fd3ed5967 100644 --- a/inferencex-e2e/perf-changelog.yaml +++ b/inferencex-e2e/perf-changelog.yaml @@ -9858,3 +9858,11 @@ - "ATOM changes in the new image that matter here: with the replay on, C256 and C384 store the PAGE KV alone in LMCache with no state image, and a hit LMCache holds past HBM loads that KV and replays below it (ROCm/ATOM#2571, #2579); DP attention points balance each lockstep prefill step by estimated chunk cost through the prefill delayer they enable (#2551); FP4 decode top-k is scored in the batch-keyed graph core and DP-padded empty tails no longer abort V4-Pro DEP decode (#2543, #2572, #2556); unconsumed LMCache lookups no longer leak L1 read locks (#2518); the compile cache is keyed on the speculative method and width (#2566)." - "No data-type or precision change to the DSpark draft: the bundled mtp.* layers of deepseek-ai/DeepSeek-V4-Pro-0813 (FP8 E4M3 attention projections, shared experts and main_proj with UE8M0 block scales, MXFP4 routed experts, BF16 norms, gate and heads) load through the target's checkpoint quant config with no online quantization, and the draft window KV follows the target's kv-cache-dtype, so at C1 to C16 it moves from BF16 to FP8 with the target, as CONTRIBUTING.md allows for an FP8 target." pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4065 + +- config-keys: + - "*" + scenario-type: + - agentic-coding + description: + - "Upgrade agentx-harness from 1.0.9 to 1.0.10: pin SPAWN subagents to one client worker to prevent duplicate session state accumulating across workers. Metric collection, calculations, and exports are unchanged." + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXX From 51cfd6cd29bbc571c2657f18a24f4c98616fb3fc Mon Sep 17 00:00:00 2001 From: Cam Quilici Date: Thu, 15 Oct 2026 10:58:12 -0500 Subject: [PATCH 2/2] docs: link AgentX 1.0.10 changelog entry to PR 4119 --- inferencex-e2e/perf-changelog.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/inferencex-e2e/perf-changelog.yaml b/inferencex-e2e/perf-changelog.yaml index 7fd3ed5967..ffb4097b55 100644 --- a/inferencex-e2e/perf-changelog.yaml +++ b/inferencex-e2e/perf-changelog.yaml @@ -9865,4 +9865,4 @@ - agentic-coding description: - "Upgrade agentx-harness from 1.0.9 to 1.0.10: pin SPAWN subagents to one client worker to prevent duplicate session state accumulating across workers. Metric collection, calculations, and exports are unchanged." - pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXX + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4119