fix: [https://nvbugspro.nvidia.com/bug/5242406][fix] Fix fp8 kvcache support

[hlu1]

Description

• Make sure thatquant_config in attention kernel is not modified later when we reset the quant_config in modules that are excluded from quantization.
• Add exclude_kv_cache to QuantMode.has_any_quant which is used in Linear and FusedMoE. This was causing issues with enabling fp8 kvcache with fp16/bf16 checkpoints.
• Remove the check under if use_paged_context_fmha and self.has_fp8_kv_cache from trtllm attention. It doesn't make any sense because Linear quant_configs are independent from kvcache quant config.
• Make sure to set the kv_cache_quant_algo with the original value when resetting quant_config for modules in quant_config.exclude_modules.

Test Coverage

GitHub Bot Help

/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...

Provide a user friendly way for developers to interact with a Jenkins server.

Run /bot [-h|--help] to print this help message.

See details below for each supported subcommand.

run [--disable-fail-fast --skip-test --stage-list "A10-1, xxx" --gpu-type "A30, H100_PCIe" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-[Post-Merge]-1, xxx"]

Launch build/test pipelines. All previously running jobs will be killed.

--disable-fail-fast (OPTIONAL) : Disable fail fast on build/tests/infra failures.

--skip-test (OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.

--stage-list "A10-1, xxx" (OPTIONAL) : Only run the specified test stages. Examples: "A10-1, xxx". Note: Does NOT update GitHub check status.

--gpu-type "A30, H100_PCIe" (OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.

--only-multi-gpu-test (OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.

--disable-multi-gpu-test (OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.

--add-multi-gpu-test (OPTIONAL) : Force run the multi-GPU tests. Will also run L0 pre-merge pipeline.

--post-merge (OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.

--extra-stage "H100_PCIe-[Post-Merge]-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-[Post-Merge]-1, xxx".

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip testing for latest commit on pull request. --comment "Reason for skipping build/test" is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

reuse-pipeline

reuse-pipeline

Reuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

[hlu1]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #3434 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #3434 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #2411 completed with status: 'FAILURE'

[hlu1]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #3444 [ run ] triggered by Bot

[tensorrt-cicd]

PR_Github #3444 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #2420 completed with status: 'SUCCESS'

[hlu1]

/bot reuse-pipeline

[tensorrt-cicd]

PR_Github #3461 [ reuse-pipeline ] triggered by Bot

[tensorrt-cicd]

PR_Github #3461 [ reuse-pipeline ] completed with state SUCCESS
Reusing PR_Github #3444 for commit 096fc40

[hlu1]

/bot reuse-pipeline

[tensorrt-cicd]

PR_Github #3652 [ reuse-pipeline ] triggered by Bot

[tensorrt-cicd]

PR_Github #3652 [ reuse-pipeline ] completed with state SUCCESS
Reusing PR_Github #3444 for commit 809b907

[hlu1]

/bot reuse-pipeline

[tensorrt-cicd]

PR_Github #3665 [ reuse-pipeline ] triggered by Bot

[tensorrt-cicd]

PR_Github #3665 [ reuse-pipeline ] completed with state SUCCESS
Reusing PR_Github #3444 for commit 46869d6