From 521fff7761eb5e70957d5bad56d94e74294da288 Mon Sep 17 00:00:00 2001 From: Cam Quilici Date: Tue, 21 Jul 2026 10:46:21 -0500 Subject: [PATCH] Restore DeepSeek-V4 tool calling for AgentX evals --- benchmarks/single_node/agentic/dsv4_fp4_b200_vllm.sh | 2 ++ perf-changelog.yaml | 10 ++++++++++ 2 files changed, 12 insertions(+) diff --git a/benchmarks/single_node/agentic/dsv4_fp4_b200_vllm.sh b/benchmarks/single_node/agentic/dsv4_fp4_b200_vllm.sh index d8ddbd608..c6f3f98c7 100755 --- a/benchmarks/single_node/agentic/dsv4_fp4_b200_vllm.sh +++ b/benchmarks/single_node/agentic/dsv4_fp4_b200_vllm.sh @@ -335,6 +335,8 @@ VLLM_CMD=( --no-enable-flashinfer-autotune --tokenizer-mode deepseek_v4 --reasoning-parser deepseek_v4 + --tool-call-parser deepseek_v4 + --enable-auto-tool-choice --attention-config '{"backend":"FLASHINFER_MLA_SPARSE_DSV4","use_prefill_query_quantization":true,"use_fp4_indexer_cache":true}' --no-disable-hybrid-kv-cache-manager --disable-uvicorn-access-log diff --git a/perf-changelog.yaml b/perf-changelog.yaml index ce40c6939..2bad762fd 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -5003,3 +5003,13 @@ - "LMCache MP server (lmcache_driven transfer mode) + LMCacheMPConnector per PR #2153; L1 pool derated to 75% of TOTAL_CPU_DRAM_GB; --enable-cumem-allocator dropped on the lmcache arm only (cuMem/VMM allocations cannot be CUDA-IPC-exported to the LMCache server)" - "LMCache TP8 points mirror the vllm-simple ladder (conc [8, 12, 16]); LMCache DEP8 points mirror the Mooncake ladder (conc [12, 20, 28, 36, 44, 52, 60, 68, 76]) for a like-for-like backend comparison; the PR #2231 bring-up sweep validated the recipe across DEP8 conc 8-80 (peak ~25.7k total tok/s/GPU at conc 72, 96-98% cache hit)" pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2231 + +- config-keys: + - dsv4-fp4-b200-vllm-agentic + scenario-type: + - agentic-coding + description: + - "Eval-only follow-up to PR #2231: restore the official DeepSeek-V4 vLLM tool-calling frontend flags --tool-call-parser deepseek_v4 and --enable-auto-tool-choice" + - "Re-run the dedicated AgentX SWE-bench eval to verify tool definitions are accepted instead of failing with 'tool parsing is disabled by frontend configuration'" + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2231 + evals-only: true