[Optim] Remove limitation of number of kvcache blocks

[Jiang-Jia-Jun]

Motivation

移除原本对kv cache block数量的限制

💡 If this PR is a Cherry Pick, the PR title needs to follow the format by adding the [Cherry-Pick] label at the very beginning and appending the original PR ID at the end. For example, [Cherry-Pick][CI] Add check trigger and logic(#5191)

💡 如若此PR是Cherry Pick，PR标题需遵循格式，在最开始加上[Cherry-Pick]标签，以及最后面加上原PR ID，例如[Cherry-Pick][CI] Add check trigger and logic(#5191)

Modifications

Usage or Command

Accuracy Tests

Checklist

• Add at least a tag in the PR title.
  • Tag list: [[FDConfig],[APIServer],[Engine], [Scheduler], [PD Disaggregation], [Executor], [Graph Optimization], [Speculative Decoding], [RL], [Models], [Quantization], [Loader], [OP], [KVCache], [DataProcessor], [BugFix], [Docs], [CI], [Optimization], [Feature], [Benchmark], [Others], [XPU], [HPU], [GCU], [DCU], [Iluvatar], [Metax]]
  • You can add new tags based on the PR content, but the semantics must be clear.
• Format your code, run pre-commit before commit.
• Add unit tests. Please write the reason in this PR if no unit tests.
• Provide accuracy results.
• If the current PR is submitting to the release branch, make sure the PR has been submitted to the develop branch, then cherry-pick it to the release branch with the [Cherry-Pick] PR tag.

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
1 out of 2 committers have signed the CLA.

✅ Jiang-Jia-Jun
❌ jiangjiajun
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[paddle-bot]

Thanks for your contribution!

[Copilot]

Pull request overview

This PR removes the hardcoded 40,000 block limit for KV cache allocation and replaces it with a configurable environment variable FD_MAX_KVCACHE_BLOCKS. This provides more flexibility for different deployment scenarios and hardware configurations.

Key Changes

• Introduced FD_MAX_KVCACHE_BLOCKS environment variable with default value of -1 (no limit)
• Updated block allocation logic in worker_process.py and iluvatar_worker.py to use the configurable limit
• Removed hardcoded 40,000 block restriction that could unnecessarily limit large memory systems

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 3 comments.

File	Description
fastdeploy/envs.py	Added FD_MAX_KVCACHE_BLOCKS environment variable configuration with default value -1
fastdeploy/worker/worker_process.py	Replaced hardcoded 40,000 limit with configurable FD_MAX_KVCACHE_BLOCKS check
fastdeploy/worker/iluvatar_worker.py	Applied same configurable limit logic as worker_process.py for consistency

Note regarding PR metadata: 根据自定义代码审查规范，PR描述应该更完整地说明：1) 为什么要移除40000的硬编码限制；2) 新环境变量的使用方法（默认值-1表示无限制）；3) 具体修改了哪些文件。此外，PR标题中的"[Optim]"标签建议改为项目标签列表中的"[Optimization]"以保持一致性。

[Copilot]

The min() function on line 542 is redundant since the condition on line 540 already ensures that num_blocks_local > envs.FD_MAX_KVCACHE_BLOCKS. You can simplify line 542 to just assign envs.FD_MAX_KVCACHE_BLOCKS directly to num_blocks_local.

Suggested change

	num_blocks_local = min(envs.FD_MAX_KVCACHE_BLOCKS, num_blocks_local)
	num_blocks_local = envs.FD_MAX_KVCACHE_BLOCKS

[Copilot]

Pull request overview

Copilot reviewed 3 out of 3 changed files in this pull request and generated no new comments.